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

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

Neuron 481 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1060009 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1095587 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0313. Min Act: -0.0001

Data Index: 652156 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0233. Min Act: -0.0001

Data Index: 754071 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1483730 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1104529 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1502793 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1042247 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0211. Min Act: -0.0001

Data Index: 400424 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1564689 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1063067 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0205. Min Act: -0.0001

Data Index: 558241 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0203. Min Act: -0.0001

Data Index: 799030 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0193. Min Act: -0.0001

Data Index: 630943 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0199. Min Act: -0.0001

Data Index: 221322 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0192. Min Act: -0.0001

Data Index: 703651 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0209. Min Act: -0.0001

Data Index: 346465 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1096096 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1197904 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0194. Min Act: -0.0001

Data Index: 748358 (C4 (Web Text))

Max Activating Token Index: 660