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

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

Neuron 279 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1308. Min Act: -0.0002

Data Index: 388742 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1130. Min Act: -0.0002

Data Index: 546598 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1102. Min Act: -0.0002

Data Index: 801333 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1106275 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1187. Min Act: -0.0002

Data Index: 136279 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1096. Min Act: -0.0002

Data Index: 49346 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1156. Min Act: -0.0002

Data Index: 321366 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1032. Min Act: -0.0002

Data Index: 377192 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1321773 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1051455 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1283666 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0958. Min Act: -0.0002

Data Index: 26137 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0991. Min Act: -0.0002

Data Index: 386061 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1026. Min Act: -0.0002

Data Index: 733873 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0947. Min Act: -0.0002

Data Index: 445041 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1020. Min Act: -0.0002

Data Index: 666877 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0865. Min Act: -0.0002

Data Index: 802685 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0890. Min Act: -0.0002

Data Index: 188739 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0887. Min Act: -0.0002

Data Index: 280334 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1216394 (C4 (Web Text))

Max Activating Token Index: 580