Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1000 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0200. Min Act: -0.0003

Data Index: 955410 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0201. Min Act: -0.0004

Data Index: 24968 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1135290 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0193. Min Act: -0.0004

Data Index: 1358453 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0193. Min Act: -0.0004

Data Index: 100181 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0196. Min Act: -0.0003

Data Index: 456812 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0196. Min Act: -0.0003

Data Index: 826892 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0195. Min Act: -0.0003

Data Index: 46299 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0195. Min Act: -0.0003

Data Index: 916417 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0195. Min Act: -0.0003

Data Index: 713628 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0190. Min Act: -0.0003

Data Index: 929810 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0194. Min Act: -0.0004

Data Index: 212968 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0189. Min Act: -0.0003

Data Index: 500315 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0197. Min Act: -0.0004

Data Index: 587205 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0192. Min Act: -0.0004

Data Index: 57626 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0192. Min Act: -0.0004

Data Index: 139117 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0188. Min Act: -0.0004

Data Index: 680121 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1230372 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0192. Min Act: -0.0004

Data Index: 1102631 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0192. Min Act: -0.0004

Data Index: 81133 (C4 (Web Text))

Max Activating Token Index: 67