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

Dataset: Open Web Text

Neuron 1465 in Layer 3

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: 3.8311. Min Range: -3.8311

Max Act: 3.8311. Min Act: -0.1700

Data Index: 6061057 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.8254. Min Act: -0.1700

Data Index: 6772392 (Open Web Text)

Max Activating Token Index: 981

Text #2

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.8189. Min Act: -0.1700

Data Index: 6486680 (Open Web Text)

Max Activating Token Index: 982

Text #3

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7761. Min Act: -0.1700

Data Index: 2361113 (Open Web Text)

Max Activating Token Index: 871

Text #4

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7806. Min Act: -0.1700

Data Index: 6631622 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7630. Min Act: -0.1700

Data Index: 1012826 (Open Web Text)

Max Activating Token Index: 843

Text #6

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7328. Min Act: -0.1700

Data Index: 7024989 (Open Web Text)

Max Activating Token Index: 809

Text #7

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7719. Min Act: -0.1700

Data Index: 2687463 (Open Web Text)

Max Activating Token Index: 878

Text #8

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7434. Min Act: -0.1700

Data Index: 7953592 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7378. Min Act: -0.1700

Data Index: 8353586 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7531. Min Act: -0.1700

Data Index: 3410048 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7597. Min Act: -0.1700

Data Index: 3591339 (Open Web Text)

Max Activating Token Index: 972

Text #12

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7154. Min Act: -0.1700

Data Index: 6736111 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7030. Min Act: -0.1700

Data Index: 6420771 (Open Web Text)

Max Activating Token Index: 552

Text #14

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7016. Min Act: -0.1700

Data Index: 3727616 (Open Web Text)

Max Activating Token Index: 937

Text #15

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.6944. Min Act: -0.1700

Data Index: 6079949 (Open Web Text)

Max Activating Token Index: 838

Text #16

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7382. Min Act: -0.1700

Data Index: 1835940 (Open Web Text)

Max Activating Token Index: 527

Text #17

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7238. Min Act: -0.1700

Data Index: 3539758 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7230. Min Act: -0.1700

Data Index: 387080 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 3.8311. Min Range: -3.8311

Max Act: 3.7195. Min Act: -0.1700

Data Index: 5988642 (Open Web Text)

Max Activating Token Index: 974