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

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

Neuron 385 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: 0.4189. Min Range: -0.4189

Max Act: 0.4189. Min Act: -0.0001

Data Index: 967022 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.4109. Min Act: -0.0001

Data Index: 526110 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3823. Min Act: -0.0001

Data Index: 702567 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3581. Min Act: -0.0001

Data Index: 865624 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3667. Min Act: -0.0001

Data Index: 43615 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1105744 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3194. Min Act: -0.0001

Data Index: 1341092 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3412. Min Act: -0.0001

Data Index: 1150649 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3402. Min Act: -0.0001

Data Index: 969693 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3307. Min Act: -0.0001

Data Index: 329011 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3133. Min Act: -0.0001

Data Index: 454670 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3436. Min Act: -0.0001

Data Index: 413602 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3235. Min Act: -0.0001

Data Index: 686396 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3229. Min Act: -0.0001

Data Index: 686774 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3239. Min Act: -0.0001

Data Index: 596457 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3188. Min Act: -0.0001

Data Index: 233919 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.2972. Min Act: -0.0001

Data Index: 397750 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1156798 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3126. Min Act: -0.0001

Data Index: 1351444 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3026. Min Act: -0.0001

Data Index: 1155612 (C4 (Web Text))

Max Activating Token Index: 279