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

Dataset: Open Web Text

Neuron 1943 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: 3.0846. Min Range: -3.0846

Max Act: 3.0846. Min Act: -0.1700

Data Index: 1495610 (Open Web Text)

Max Activating Token Index: 807

Text #1

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0239. Min Act: -0.1700

Data Index: 344203 (Open Web Text)

Max Activating Token Index: 832

Text #2

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0075. Min Act: -0.1700

Data Index: 4466845 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 3.0846. Min Range: -3.0846

Max Act: 3.0345. Min Act: -0.1700

Data Index: 2259988 (Open Web Text)

Max Activating Token Index: 868

Text #4

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9820. Min Act: -0.1700

Data Index: 4320128 (Open Web Text)

Max Activating Token Index: 922

Text #5

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9637. Min Act: -0.1700

Data Index: 69964 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9602. Min Act: -0.1700

Data Index: 2350094 (Open Web Text)

Max Activating Token Index: 806

Text #7

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9637. Min Act: -0.1700

Data Index: 1503405 (Open Web Text)

Max Activating Token Index: 399

Text #8

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9484. Min Act: -0.1700

Data Index: 8569321 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9071. Min Act: -0.1700

Data Index: 230715 (Open Web Text)

Max Activating Token Index: 771

Text #10

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9456. Min Act: -0.1700

Data Index: 2028970 (Open Web Text)

Max Activating Token Index: 848

Text #11

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9540. Min Act: -0.1700

Data Index: 4253753 (Open Web Text)

Max Activating Token Index: 822

Text #12

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9349. Min Act: -0.1700

Data Index: 5004551 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9358. Min Act: -0.1700

Data Index: 7311839 (Open Web Text)

Max Activating Token Index: 838

Text #14

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9379. Min Act: -0.1700

Data Index: 1690191 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9308. Min Act: -0.1700

Data Index: 5246248 (Open Web Text)

Max Activating Token Index: 379

Text #16

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9241. Min Act: -0.1700

Data Index: 2892635 (Open Web Text)

Max Activating Token Index: 243

Text #17

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9346. Min Act: -0.1700

Data Index: 5410843 (Open Web Text)

Max Activating Token Index: 296

Text #18

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9204. Min Act: -0.1700

Data Index: 3786722 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.0846. Min Range: -3.0846

Max Act: 2.9121. Min Act: -0.1700

Data Index: 4383714 (Open Web Text)

Max Activating Token Index: 976