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

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

Neuron 2800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0003

Data Index: 321196 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0275. Min Act: -0.0003

Data Index: 776483 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0243. Min Act: -0.0003

Data Index: 400181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0179. Min Act: -0.0002

Data Index: 964401 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0226. Min Act: -0.0003

Data Index: 804251 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0216. Min Act: -0.0003

Data Index: 874287 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0159. Min Act: -0.0003

Data Index: 253652 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0266. Min Act: -0.0003

Data Index: 86773 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0235. Min Act: -0.0003

Data Index: 747359 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0264. Min Act: -0.0003

Data Index: 897960 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0159. Min Act: -0.0003

Data Index: 229297 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1029451 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0138. Min Act: -0.0003

Data Index: 99058 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0207. Min Act: -0.0003

Data Index: 29955 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0195. Min Act: -0.0003

Data Index: 699375 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1550799 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0202. Min Act: -0.0003

Data Index: 457739 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0228. Min Act: -0.0003

Data Index: 511511 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0178. Min Act: -0.0003

Data Index: 256590 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0188. Min Act: -0.0002

Data Index: 689442 (C4 (Web Text))

Max Activating Token Index: 1023