Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1507 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0285. Min Act: -0.0005

Data Index: 259082 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0232. Min Act: -0.0005

Data Index: 385570 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0199. Min Act: -0.0005

Data Index: 3324 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0202. Min Act: -0.0005

Data Index: 486320 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0197. Min Act: -0.0005

Data Index: 1214314 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0195. Min Act: -0.0005

Data Index: 275556 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0188. Min Act: -0.0005

Data Index: 1273530 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0184. Min Act: -0.0005

Data Index: 982862 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0183. Min Act: -0.0005

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0184. Min Act: -0.0005

Data Index: 544903 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1056588 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0182. Min Act: -0.0005

Data Index: 377654 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0182. Min Act: -0.0005

Data Index: 668044 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0179. Min Act: -0.0005

Data Index: 869839 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0178. Min Act: -0.0005

Data Index: 657764 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1040780 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0177. Min Act: -0.0005

Data Index: 1226903 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1332690 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1026627 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0176. Min Act: -0.0005

Data Index: 297311 (C4 (Web Text))

Max Activating Token Index: 164