Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3524 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1804. Min Act: -0.0000

Data Index: 919643 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1685. Min Act: -0.0000

Data Index: 365185 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1432. Min Act: -0.0000

Data Index: 528938 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1373. Min Act: -0.0000

Data Index: 166468 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1286698 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1274. Min Act: -0.0000

Data Index: 325123 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1234. Min Act: -0.0000

Data Index: 16671 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1212. Min Act: -0.0000

Data Index: 551795 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1202. Min Act: -0.0000

Data Index: 737500 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1598698 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1152. Min Act: -0.0000

Data Index: 702247 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1180. Min Act: -0.0000

Data Index: 683330 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1152880 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1311773 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1311656 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0996. Min Act: -0.0000

Data Index: 101193 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1236314 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1056. Min Act: -0.0000

Data Index: 522781 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1262307 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1211381 (C4 (Web Text))

Max Activating Token Index: 872