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

Dataset: Open Web Text

Neuron 783 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: 1.9089. Min Range: -1.9089

Max Act: 1.9089. Min Act: -0.1700

Data Index: 6241315 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8867. Min Act: -0.1700

Data Index: 7382590 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8452. Min Act: -0.1700

Data Index: 1033269 (Open Web Text)

Max Activating Token Index: 815

Text #3

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8457. Min Act: -0.1700

Data Index: 1234936 (Open Web Text)

Max Activating Token Index: 1006

Text #4

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8426. Min Act: -0.1700

Data Index: 5499348 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8602. Min Act: -0.1700

Data Index: 1083999 (Open Web Text)

Max Activating Token Index: 783

Text #6

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8188. Min Act: -0.1700

Data Index: 6740375 (Open Web Text)

Max Activating Token Index: 974

Text #7

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8283. Min Act: -0.1700

Data Index: 217453 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8064. Min Act: -0.1700

Data Index: 7760105 (Open Web Text)

Max Activating Token Index: 802

Text #9

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8244. Min Act: -0.1700

Data Index: 4305589 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8278. Min Act: -0.1700

Data Index: 1838688 (Open Web Text)

Max Activating Token Index: 154

Text #11

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8300. Min Act: -0.1700

Data Index: 5194440 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8125. Min Act: -0.1700

Data Index: 5787980 (Open Web Text)

Max Activating Token Index: 902

Text #13

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8235. Min Act: -0.1700

Data Index: 3155991 (Open Web Text)

Max Activating Token Index: 190

Text #14

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8144. Min Act: -0.1700

Data Index: 1125445 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8121. Min Act: -0.1700

Data Index: 8370913 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8174. Min Act: -0.1700

Data Index: 7238453 (Open Web Text)

Max Activating Token Index: 667

Text #17

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.7979. Min Act: -0.1700

Data Index: 704171 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.8048. Min Act: -0.1700

Data Index: 5246798 (Open Web Text)

Max Activating Token Index: 51

Text #19

Max Range: 1.9089. Min Range: -1.9089

Max Act: 1.7944. Min Act: -0.1700

Data Index: 4844774 (Open Web Text)

Max Activating Token Index: 928