< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1317 in Layer 4

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: 2.6653. Min Range: -2.6653

Max Act: 2.6653. Min Act: -0.1700

Data Index: 6459444 (Open Web Text)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.5614. Min Act: -0.1700

Data Index: 8618553 (Open Web Text)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.5814. Min Act: -0.1700

Data Index: 2021962 (Open Web Text)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.5145. Min Act: -0.1700

Data Index: 5786047 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.4761. Min Act: -0.1700

Data Index: 265354 (Open Web Text)

Max Activating Token Index: 395

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.4441. Min Act: -0.1700

Data Index: 4018904 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.4309. Min Act: -0.1700

Data Index: 5890644 (Open Web Text)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.4922. Min Act: -0.1700

Data Index: 837277 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.4326. Min Act: -0.1700

Data Index: 4913457 (Open Web Text)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.4139. Min Act: -0.1700

Data Index: 1815734 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3921. Min Act: -0.1700

Data Index: 705094 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3820. Min Act: -0.1700

Data Index: 2510274 (Open Web Text)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3623. Min Act: -0.1700

Data Index: 8261537 (Open Web Text)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3574. Min Act: -0.1700

Data Index: 5849671 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3622. Min Act: -0.1700

Data Index: 7771605 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3478. Min Act: -0.1700

Data Index: 639339 (Open Web Text)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3513. Min Act: -0.1700

Data Index: 3681286 (Open Web Text)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3379. Min Act: -0.1700

Data Index: 147185 (Open Web Text)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3149. Min Act: -0.1700

Data Index: 5540887 (Open Web Text)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6653. Min Range: -2.6653

Max Act: 2.3256. Min Act: -0.1700

Data Index: 5403743 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #19