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

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

Neuron 1564 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0002

Data Index: 285207 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0250. Min Act: -0.0003

Data Index: 376119 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0261. Min Act: -0.0003

Data Index: 734098 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0217. Min Act: -0.0003

Data Index: 418420 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0209. Min Act: -0.0003

Data Index: 714947 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0210. Min Act: -0.0003

Data Index: 425822 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0206. Min Act: -0.0004

Data Index: 296970 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0216. Min Act: -0.0003

Data Index: 144011 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0213. Min Act: -0.0003

Data Index: 779422 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0205. Min Act: -0.0003

Data Index: 297796 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0195. Min Act: -0.0003

Data Index: 597985 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1252934 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0194. Min Act: -0.0002

Data Index: 660572 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0189. Min Act: -0.0003

Data Index: 520757 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0186. Min Act: -0.0003

Data Index: 469188 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1296447 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1329019 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1003826 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0184. Min Act: -0.0003

Data Index: 803206 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0192. Min Act: -0.0003

Data Index: 732954 (C4 (Web Text))

Max Activating Token Index: 136