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

Dataset: Open Web Text

Neuron 456 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: 4.1239. Min Range: -4.1239

Max Act: 4.1239. Min Act: -0.1700

Data Index: 5927992 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.1239. Min Range: -4.1239

Max Act: 4.0425. Min Act: -0.1700

Data Index: 1276086 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.1239. Min Range: -4.1239

Max Act: 4.0166. Min Act: -0.1700

Data Index: 7481504 (Open Web Text)

Max Activating Token Index: 529

Text #3

Max Range: 4.1239. Min Range: -4.1239

Max Act: 4.0932. Min Act: -0.1700

Data Index: 2372792 (Open Web Text)

Max Activating Token Index: 278

Text #4

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.9719. Min Act: -0.1700

Data Index: 2890509 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.9279. Min Act: -0.1700

Data Index: 2890514 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.9101. Min Act: -0.1700

Data Index: 4524971 (Open Web Text)

Max Activating Token Index: 786

Text #7

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.9001. Min Act: -0.1700

Data Index: 6838855 (Open Web Text)

Max Activating Token Index: 771

Text #8

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.9266. Min Act: -0.1700

Data Index: 2890497 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.9001. Min Act: -0.1700

Data Index: 2185207 (Open Web Text)

Max Activating Token Index: 780

Text #10

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8986. Min Act: -0.1700

Data Index: 5493647 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8783. Min Act: -0.1700

Data Index: 7297476 (Open Web Text)

Max Activating Token Index: 924

Text #12

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8693. Min Act: -0.1700

Data Index: 1884616 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8398. Min Act: -0.1700

Data Index: 8426469 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8533. Min Act: -0.1700

Data Index: 3332941 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8901. Min Act: -0.1700

Data Index: 2890512 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8707. Min Act: -0.1700

Data Index: 7400188 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8835. Min Act: -0.1700

Data Index: 4759570 (Open Web Text)

Max Activating Token Index: 154

Text #18

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8833. Min Act: -0.1700

Data Index: 2475141 (Open Web Text)

Max Activating Token Index: 623

Text #19

Max Range: 4.1239. Min Range: -4.1239

Max Act: 3.8455. Min Act: -0.1700

Data Index: 6398011 (Open Web Text)

Max Activating Token Index: 337