Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 912 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0006

Data Index: 501731 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1245865 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0217. Min Act: -0.0006

Data Index: 939344 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0226. Min Act: -0.0006

Data Index: 940148 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1285040 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1207448 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1002657 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0189. Min Act: -0.0005

Data Index: 718031 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0186. Min Act: -0.0006

Data Index: 113644 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0189. Min Act: -0.0006

Data Index: 791510 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1442212 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0181. Min Act: -0.0006

Data Index: 123887 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0181. Min Act: -0.0006

Data Index: 107008 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1117167 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1259700 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0176. Min Act: -0.0006

Data Index: 713173 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1256065 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0183. Min Act: -0.0006

Data Index: 462696 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0173. Min Act: -0.0006

Data Index: 122937 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0169. Min Act: -0.0006

Data Index: 314107 (C4 (Web Text))

Max Activating Token Index: 365