< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2434 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.9825. Min Act: -0.1700

Data Index: 755481 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.9388. Min Act: -0.1700

Data Index: 3692874 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.8271. Min Act: -0.1700

Data Index: 3894374 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.8611. Min Act: -0.1700

Data Index: 5305131 (Open Web Text)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.8203. Min Act: -0.1700

Data Index: 4124801 (Open Web Text)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.8218. Min Act: -0.1700

Data Index: 5237197 (Open Web Text)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.8203. Min Act: -0.1700

Data Index: 7808411 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7530. Min Act: -0.1700

Data Index: 6766007 (Open Web Text)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7527. Min Act: -0.1700

Data Index: 8000644 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7877. Min Act: -0.1700

Data Index: 2171620 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7647. Min Act: -0.1700

Data Index: 8180103 (Open Web Text)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7452. Min Act: -0.1700

Data Index: 4098666 (Open Web Text)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7462. Min Act: -0.1700

Data Index: 6621752 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7261. Min Act: -0.1700

Data Index: 6458118 (Open Web Text)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7425. Min Act: -0.1700

Data Index: 7056421 (Open Web Text)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7440. Min Act: -0.1700

Data Index: 1331852 (Open Web Text)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7395. Min Act: -0.1700

Data Index: 4780963 (Open Web Text)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7621. Min Act: -0.1700

Data Index: 8042307 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7747. Min Act: -0.1700

Data Index: 3896109 (Open Web Text)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9825. Min Range: -2.9825

Max Act: 2.7325. Min Act: -0.1700

Data Index: 3303945 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #19