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

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

Neuron 388 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: 0.0214. Min Range: -0.0214

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1133837 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1218363 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0204. Min Act: -0.0003

Data Index: 842294 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1113715 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0201. Min Act: -0.0003

Data Index: 304392 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1119557 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1229343 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0200. Min Act: -0.0002

Data Index: 245768 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0203. Min Act: -0.0001

Data Index: 407110 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0196. Min Act: -0.0002

Data Index: 622729 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0001

Data Index: 649670 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1343576 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0003

Data Index: 855191 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0190. Min Act: -0.0003

Data Index: 25570 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1181426 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0183. Min Act: -0.0003

Data Index: 838930 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0189. Min Act: -0.0003

Data Index: 847640 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1111302 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0182. Min Act: -0.0002

Data Index: 444710 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0182. Min Act: -0.0002

Data Index: 71236 (C4 (Web Text))

Max Activating Token Index: 123