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

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

Neuron 5103 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2311. Min Range: -1.2311

Max Act: 1.2311. Min Act: -0.0001

Data Index: 174495 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.2311. Min Range: -1.2311

Max Act: 1.0873. Min Act: -0.0001

Data Index: 342829 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 1.2311. Min Range: -1.2311

Max Act: 1.0337. Min Act: -0.0001

Data Index: 166443 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.2311. Min Range: -1.2311

Max Act: 1.0329. Min Act: -0.0001

Data Index: 593263 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9774. Min Act: -0.0001

Data Index: 1181193 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9119. Min Act: -0.0001

Data Index: 752356 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9797. Min Act: -0.0001

Data Index: 492581 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9199. Min Act: -0.0001

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8787. Min Act: -0.0001

Data Index: 238503 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9045. Min Act: -0.0001

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9755. Min Act: -0.0001

Data Index: 184798 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8667. Min Act: -0.0001

Data Index: 634070 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9632. Min Act: -0.0001

Data Index: 686893 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8911. Min Act: -0.0001

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8713. Min Act: -0.0001

Data Index: 551575 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.9083. Min Act: -0.0001

Data Index: 1007079 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8889. Min Act: -0.0001

Data Index: 1834 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8158. Min Act: -0.0001

Data Index: 478343 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8888. Min Act: -0.0001

Data Index: 790687 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.8510. Min Act: -0.0001

Data Index: 251624 (C4 (Web Text))

Max Activating Token Index: 339