< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2027 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: 2.0218. Min Range: -2.0218

Max Act: 2.0218. Min Act: -0.1700

Data Index: 2673944 (Open Web Text)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0218. Min Range: -2.0218

Max Act: 2.0116. Min Act: -0.1700

Data Index: 2858872 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9579. Min Act: -0.1700

Data Index: 6292675 (Open Web Text)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9629. Min Act: -0.1700

Data Index: 4534518 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9725. Min Act: -0.1700

Data Index: 3324238 (Open Web Text)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9480. Min Act: -0.1700

Data Index: 3126644 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9795. Min Act: -0.1700

Data Index: 1579588 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9581. Min Act: -0.1700

Data Index: 617460 (Open Web Text)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9524. Min Act: -0.1700

Data Index: 7883325 (Open Web Text)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9618. Min Act: -0.1700

Data Index: 5480131 (Open Web Text)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9416. Min Act: -0.1700

Data Index: 8766543 (Open Web Text)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9572. Min Act: -0.1700

Data Index: 7029980 (Open Web Text)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9561. Min Act: -0.1700

Data Index: 5147017 (Open Web Text)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9509. Min Act: -0.1700

Data Index: 6239408 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9394. Min Act: -0.1700

Data Index: 3065050 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9324. Min Act: -0.1700

Data Index: 5621118 (Open Web Text)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9309. Min Act: -0.1700

Data Index: 6189630 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9495. Min Act: -0.1700

Data Index: 3884259 (Open Web Text)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9421. Min Act: -0.1700

Data Index: 1850792 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0218. Min Range: -2.0218

Max Act: 1.9334. Min Act: -0.1700

Data Index: 1839090 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #19