Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3688 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1449. Min Act: -0.0002

Data Index: 740176 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1304. Min Act: -0.0001

Data Index: 430562 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1311672 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1414. Min Act: -0.0002

Data Index: 815358 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1358. Min Act: -0.0001

Data Index: 910001 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1274. Min Act: -0.0002

Data Index: 693291 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1215. Min Act: -0.0002

Data Index: 977805 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1338. Min Act: -0.0002

Data Index: 263237 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1249. Min Act: -0.0002

Data Index: 1015435 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1175. Min Act: -0.0001

Data Index: 906555 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1155. Min Act: -0.0002

Data Index: 393341 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1232. Min Act: -0.0002

Data Index: 677318 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1072. Min Act: -0.0001

Data Index: 466110 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1174. Min Act: -0.0002

Data Index: 486073 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1123. Min Act: -0.0002

Data Index: 435991 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1191851 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1145. Min Act: -0.0001

Data Index: 403088 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1110. Min Act: -0.0001

Data Index: 89561 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1191. Min Act: -0.0002

Data Index: 368466 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1190. Min Act: -0.0002

Data Index: 335647 (C4 (Web Text))

Max Activating Token Index: 268