Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2344 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3755. Min Act: -0.0000

Data Index: 187929 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3385. Min Act: -0.0001

Data Index: 595778 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3319. Min Act: -0.0000

Data Index: 588004 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1302186 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3130. Min Act: -0.0001

Data Index: 262977 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3129. Min Act: -0.0000

Data Index: 461698 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2972. Min Act: -0.0001

Data Index: 507923 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3281. Min Act: -0.0001

Data Index: 225399 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3287. Min Act: -0.0001

Data Index: 541992 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3178. Min Act: -0.0001

Data Index: 204141 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3359. Min Act: -0.0001

Data Index: 733233 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3218. Min Act: -0.0001

Data Index: 552461 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3229. Min Act: -0.0000

Data Index: 969563 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1120660 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3036. Min Act: -0.0000

Data Index: 336166 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1092427 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1269814 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1348855 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3176. Min Act: -0.0001

Data Index: 820320 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2911. Min Act: -0.0000

Data Index: 641285 (C4 (Web Text))

Max Activating Token Index: 837