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

Dataset: Open Web Text

Neuron 774 in Layer 2

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: 3.7707. Min Range: -3.7707

Max Act: 3.7707. Min Act: -0.1700

Data Index: 7931254 (Open Web Text)

Max Activating Token Index: 448

Text #1

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.7692. Min Act: -0.1700

Data Index: 599584 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.7629. Min Act: -0.1700

Data Index: 400527 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.7116. Min Act: -0.1700

Data Index: 7931251 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.7186. Min Act: -0.1700

Data Index: 6289587 (Open Web Text)

Max Activating Token Index: 60

Text #5

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.7070. Min Act: -0.1700

Data Index: 1141912 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6785. Min Act: -0.1700

Data Index: 1122791 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6754. Min Act: -0.1700

Data Index: 3683751 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6885. Min Act: -0.1700

Data Index: 7931253 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6934. Min Act: -0.1700

Data Index: 2479026 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6622. Min Act: -0.1700

Data Index: 2131663 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6582. Min Act: -0.1700

Data Index: 7921879 (Open Web Text)

Max Activating Token Index: 847

Text #12

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6325. Min Act: -0.1700

Data Index: 1678475 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6457. Min Act: -0.1700

Data Index: 6165090 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6298. Min Act: -0.1700

Data Index: 34299 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6192. Min Act: -0.1700

Data Index: 8598370 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6225. Min Act: -0.1700

Data Index: 5697632 (Open Web Text)

Max Activating Token Index: 881

Text #17

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6206. Min Act: -0.1700

Data Index: 8681623 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6296. Min Act: -0.1700

Data Index: 2479030 (Open Web Text)

Max Activating Token Index: 210

Text #19

Max Range: 3.7707. Min Range: -3.7707

Max Act: 3.6230. Min Act: -0.1700

Data Index: 6466107 (Open Web Text)

Max Activating Token Index: 447