< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2523 in Layer 0

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: 2.9816. Min Range: -2.9816

Max Act: 2.9816. Min Act: -0.1700

Data Index: 3261547 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.9196. Min Act: -0.1700

Data Index: 4275610 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8566. Min Act: -0.1700

Data Index: 884243 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8508. Min Act: -0.1700

Data Index: 3623809 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8545. Min Act: -0.1700

Data Index: 8736801 (Open Web Text)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8530. Min Act: -0.1700

Data Index: 5370966 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8351. Min Act: -0.1700

Data Index: 5489096 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8151. Min Act: -0.1700

Data Index: 5750550 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8206. Min Act: -0.1700

Data Index: 8821107 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8156. Min Act: -0.1700

Data Index: 711345 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8192. Min Act: -0.1700

Data Index: 705237 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8160. Min Act: -0.1700

Data Index: 8222907 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8234. Min Act: -0.1700

Data Index: 7569651 (Open Web Text)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8249. Min Act: -0.1700

Data Index: 4342921 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.7989. Min Act: -0.1700

Data Index: 4859430 (Open Web Text)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8055. Min Act: -0.1700

Data Index: 6412019 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.8038. Min Act: -0.1700

Data Index: 3955047 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.7846. Min Act: -0.1700

Data Index: 5724840 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.7866. Min Act: -0.1700

Data Index: 767259 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9816. Min Range: -2.9816

Max Act: 2.7749. Min Act: -0.1700

Data Index: 1701234 (Open Web Text)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #19