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

Dataset: Open Web Text

Neuron 997 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: 5.3228. Min Range: -5.3228

Max Act: 5.3194. Min Act: -0.1700

Data Index: 7964558 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.3228. Min Act: -0.1700

Data Index: 7513401 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2767. Min Act: -0.1700

Data Index: 8613793 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2828. Min Act: -0.1700

Data Index: 7901761 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2632. Min Act: -0.1700

Data Index: 2658465 (Open Web Text)

Max Activating Token Index: 179

Text #5

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2746. Min Act: -0.1700

Data Index: 2314442 (Open Web Text)

Max Activating Token Index: 660

Text #6

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2305. Min Act: -0.1700

Data Index: 4586009 (Open Web Text)

Max Activating Token Index: 937

Text #7

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2633. Min Act: -0.1700

Data Index: 1053435 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2426. Min Act: -0.1700

Data Index: 3947765 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2383. Min Act: -0.1700

Data Index: 5100988 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2349. Min Act: -0.1700

Data Index: 669843 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2508. Min Act: -0.1700

Data Index: 4872844 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2459. Min Act: -0.1700

Data Index: 3495782 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2433. Min Act: -0.1700

Data Index: 7749316 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2234. Min Act: -0.1700

Data Index: 8491862 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2257. Min Act: -0.1700

Data Index: 8598172 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2350. Min Act: -0.1700

Data Index: 634359 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2190. Min Act: -0.1700

Data Index: 1760942 (Open Web Text)

Max Activating Token Index: 932

Text #18

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.1998. Min Act: -0.1700

Data Index: 4789329 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 5.3228. Min Range: -5.3228

Max Act: 5.2507. Min Act: -0.1700

Data Index: 2020702 (Open Web Text)

Max Activating Token Index: 1022