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

Dataset: Open Web Text

Neuron 1856 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: 4.3398. Min Range: -4.3398

Max Act: 4.3398. Min Act: -0.1700

Data Index: 8741504 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.3363. Min Act: -0.1700

Data Index: 4749465 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.3363. Min Act: -0.1700

Data Index: 1221182 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2828. Min Act: -0.1700

Data Index: 1081023 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2828. Min Act: -0.1700

Data Index: 1709530 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2540. Min Act: -0.1700

Data Index: 352400 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2620. Min Act: -0.1700

Data Index: 1936536 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2415. Min Act: -0.1700

Data Index: 8754334 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2806. Min Act: -0.1700

Data Index: 6729147 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2219. Min Act: -0.1700

Data Index: 4466501 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2425. Min Act: -0.1700

Data Index: 4720474 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2257. Min Act: -0.1700

Data Index: 1198412 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2420. Min Act: -0.1700

Data Index: 708568 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2347. Min Act: -0.1700

Data Index: 1575391 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2165. Min Act: -0.1700

Data Index: 5206174 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2257. Min Act: -0.1700

Data Index: 5753750 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2257. Min Act: -0.1700

Data Index: 7960138 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2282. Min Act: -0.1700

Data Index: 2515188 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2252. Min Act: -0.1700

Data Index: 8383605 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.3398. Min Range: -4.3398

Max Act: 4.2335. Min Act: -0.1700

Data Index: 6610079 (Open Web Text)

Max Activating Token Index: 4