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

Dataset: Open Web Text

Neuron 220 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: 3.5242. Min Range: -3.5242

Max Act: 3.5242. Min Act: -0.1700

Data Index: 6827982 (Open Web Text)

Max Activating Token Index: 645

Text #1

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4737. Min Act: -0.1700

Data Index: 4631555 (Open Web Text)

Max Activating Token Index: 495

Text #2

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4940. Min Act: -0.1700

Data Index: 6149946 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4803. Min Act: -0.1700

Data Index: 1087679 (Open Web Text)

Max Activating Token Index: 271

Text #4

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4384. Min Act: -0.1700

Data Index: 8672490 (Open Web Text)

Max Activating Token Index: 953

Text #5

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4304. Min Act: -0.1700

Data Index: 8797863 (Open Web Text)

Max Activating Token Index: 335

Text #6

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4228. Min Act: -0.1700

Data Index: 4934665 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4145. Min Act: -0.1700

Data Index: 7726671 (Open Web Text)

Max Activating Token Index: 150

Text #8

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3970. Min Act: -0.1700

Data Index: 8079495 (Open Web Text)

Max Activating Token Index: 920

Text #9

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4240. Min Act: -0.1700

Data Index: 3765706 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.4000. Min Act: -0.1700

Data Index: 2536016 (Open Web Text)

Max Activating Token Index: 924

Text #11

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3663. Min Act: -0.1700

Data Index: 8491442 (Open Web Text)

Max Activating Token Index: 398

Text #12

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3852. Min Act: -0.1700

Data Index: 5551955 (Open Web Text)

Max Activating Token Index: 311

Text #13

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3480. Min Act: -0.1700

Data Index: 561331 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3638. Min Act: -0.1700

Data Index: 365249 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3804. Min Act: -0.1700

Data Index: 877688 (Open Web Text)

Max Activating Token Index: 400

Text #16

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3606. Min Act: -0.1700

Data Index: 5135564 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3613. Min Act: -0.1700

Data Index: 4615348 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3603. Min Act: -0.1700

Data Index: 8564809 (Open Web Text)

Max Activating Token Index: 904

Text #19

Max Range: 3.5242. Min Range: -3.5242

Max Act: 3.3118. Min Act: -0.1700

Data Index: 1335209 (Open Web Text)

Max Activating Token Index: 967