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

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

Neuron 2105 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: 0.0210. Min Range: -0.0210

Max Act: 0.0198. Min Act: -0.0003

Data Index: 322354 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0003

Data Index: 56320 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0197. Min Act: -0.0003

Data Index: 350145 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0199. Min Act: -0.0003

Data Index: 113325 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0197. Min Act: -0.0002

Data Index: 986055 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0003

Data Index: 483510 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0186. Min Act: -0.0003

Data Index: 312707 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0184. Min Act: -0.0003

Data Index: 905385 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0196. Min Act: -0.0003

Data Index: 894997 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0181. Min Act: -0.0003

Data Index: 987433 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0189. Min Act: -0.0003

Data Index: 756837 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1340120 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0183. Min Act: -0.0002

Data Index: 80833 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1019907 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0165. Min Act: -0.0003

Data Index: 39772 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0175. Min Act: -0.0003

Data Index: 923254 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0191. Min Act: -0.0003

Data Index: 251740 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0170. Min Act: -0.0003

Data Index: 908236 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1079665 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0177. Min Act: -0.0003

Data Index: 17043 (C4 (Web Text))

Max Activating Token Index: 964