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

Dataset: Open Web Text

Neuron 1868 in Layer 6

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: 4.1982. Min Range: -4.1982

Max Act: 4.1896. Min Act: -0.1700

Data Index: 1858226 (Open Web Text)

Max Activating Token Index: 846

Text #1

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1982. Min Act: -0.1700

Data Index: 2022021 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1508. Min Act: -0.1700

Data Index: 8516892 (Open Web Text)

Max Activating Token Index: 756

Text #3

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0732. Min Act: -0.1700

Data Index: 5155352 (Open Web Text)

Max Activating Token Index: 998

Text #4

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1375. Min Act: -0.1700

Data Index: 4531764 (Open Web Text)

Max Activating Token Index: 430

Text #5

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1528. Min Act: -0.1700

Data Index: 5872165 (Open Web Text)

Max Activating Token Index: 225

Text #6

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1318. Min Act: -0.1700

Data Index: 4465161 (Open Web Text)

Max Activating Token Index: 450

Text #7

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1199. Min Act: -0.1700

Data Index: 7462638 (Open Web Text)

Max Activating Token Index: 856

Text #8

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1065. Min Act: -0.1700

Data Index: 6542992 (Open Web Text)

Max Activating Token Index: 608

Text #9

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1188. Min Act: -0.1700

Data Index: 4271517 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0895. Min Act: -0.1700

Data Index: 8294667 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1222. Min Act: -0.1700

Data Index: 4836874 (Open Web Text)

Max Activating Token Index: 658

Text #12

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.1132. Min Act: -0.1700

Data Index: 3591178 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0697. Min Act: -0.1700

Data Index: 8374477 (Open Web Text)

Max Activating Token Index: 678

Text #14

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0909. Min Act: -0.1700

Data Index: 4486045 (Open Web Text)

Max Activating Token Index: 719

Text #15

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0825. Min Act: -0.1700

Data Index: 929195 (Open Web Text)

Max Activating Token Index: 234

Text #16

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0418. Min Act: -0.1700

Data Index: 5007662 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0144. Min Act: -0.1700

Data Index: 1352274 (Open Web Text)

Max Activating Token Index: 912

Text #18

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0467. Min Act: -0.1700

Data Index: 5086304 (Open Web Text)

Max Activating Token Index: 111

Text #19

Max Range: 4.1982. Min Range: -4.1982

Max Act: 4.0358. Min Act: -0.1700

Data Index: 3169252 (Open Web Text)

Max Activating Token Index: 583