Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2036 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0004

Data Index: 1112481 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0221. Min Act: -0.0004

Data Index: 1075778 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1265267 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0216. Min Act: -0.0004

Data Index: 898444 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0207. Min Act: -0.0004

Data Index: 336504 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0203. Min Act: -0.0004

Data Index: 40187 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0202. Min Act: -0.0004

Data Index: 138774 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0209. Min Act: -0.0004

Data Index: 1335532 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0195. Min Act: -0.0004

Data Index: 192659 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0195. Min Act: -0.0004

Data Index: 100447 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0193. Min Act: -0.0004

Data Index: 335296 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0193. Min Act: -0.0004

Data Index: 181242 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0195. Min Act: -0.0004

Data Index: 193680 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0195. Min Act: -0.0004

Data Index: 834802 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0198. Min Act: -0.0004

Data Index: 36181 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0194. Min Act: -0.0004

Data Index: 830254 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0183. Min Act: -0.0004

Data Index: 180152 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0194. Min Act: -0.0004

Data Index: 1519414 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1610719 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0187. Min Act: -0.0004

Data Index: 158032 (C4 (Web Text))

Max Activating Token Index: 644