< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 465 in Layer 1

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: 2.1339. Min Range: -2.1339

Max Act: 2.1339. Min Act: -0.1700

Data Index: 6577738 (Open Web Text)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.1041. Min Act: -0.1699

Data Index: 948321 (Open Web Text)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0676. Min Act: -0.1700

Data Index: 3486631 (Open Web Text)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0678. Min Act: -0.1700

Data Index: 2549084 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0720. Min Act: -0.1700

Data Index: 3466411 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0561. Min Act: -0.1700

Data Index: 3626628 (Open Web Text)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0517. Min Act: -0.1700

Data Index: 7039758 (Open Web Text)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0420. Min Act: -0.1699

Data Index: 163010 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0345. Min Act: -0.1700

Data Index: 872051 (Open Web Text)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0476. Min Act: -0.1700

Data Index: 2527991 (Open Web Text)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0399. Min Act: -0.1700

Data Index: 7418779 (Open Web Text)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0534. Min Act: -0.1700

Data Index: 6577737 (Open Web Text)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0376. Min Act: -0.1700

Data Index: 6249172 (Open Web Text)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0388. Min Act: -0.1699

Data Index: 163012 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0382. Min Act: -0.1700

Data Index: 3515639 (Open Web Text)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0467. Min Act: -0.1700

Data Index: 5518915 (Open Web Text)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0248. Min Act: -0.1700

Data Index: 8259785 (Open Web Text)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0234. Min Act: -0.1700

Data Index: 6038359 (Open Web Text)

Max Activating Token Index: 236

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0317. Min Act: -0.1700

Data Index: 978148 (Open Web Text)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1339. Min Range: -2.1339

Max Act: 2.0077. Min Act: -0.1700

Data Index: 4350759 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #19