Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4350 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1316. Min Act: -0.0002

Data Index: 702756 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0002

Data Index: 176936 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1240. Min Act: -0.0002

Data Index: 83405 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1233. Min Act: -0.0002

Data Index: 532557 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1138. Min Act: -0.0002

Data Index: 15226 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1178. Min Act: -0.0002

Data Index: 779340 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1254. Min Act: -0.0002

Data Index: 83992 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1066. Min Act: -0.0002

Data Index: 7403 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1162. Min Act: -0.0002

Data Index: 606807 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1207. Min Act: -0.0002

Data Index: 983721 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1156. Min Act: -0.0002

Data Index: 556335 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1185741 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1264. Min Act: -0.0002

Data Index: 938167 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1174. Min Act: -0.0002

Data Index: 479402 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1332. Min Act: -0.0002

Data Index: 472538 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1211. Min Act: -0.0002

Data Index: 913859 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1137. Min Act: -0.0002

Data Index: 899134 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1076. Min Act: -0.0002

Data Index: 9513 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1252. Min Act: -0.0002

Data Index: 733251 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1191. Min Act: -0.0002

Data Index: 323606 (C4 (Web Text))

Max Activating Token Index: 662