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

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

Neuron 167 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5526. Min Act: -0.0001

Data Index: 721598 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5092. Min Act: -0.0001

Data Index: 616276 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5498. Min Act: -0.0001

Data Index: 532265 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5902. Min Act: -0.0001

Data Index: 32082 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5195. Min Act: -0.0001

Data Index: 150148 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5930. Min Act: -0.0001

Data Index: 143172 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5437. Min Act: -0.0001

Data Index: 1261701 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5355. Min Act: -0.0001

Data Index: 259988 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5730. Min Act: -0.0001

Data Index: 336828 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5430. Min Act: -0.0001

Data Index: 526656 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5230. Min Act: -0.0001

Data Index: 533322 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5273. Min Act: -0.0001

Data Index: 459493 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5380. Min Act: -0.0001

Data Index: 436803 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1293439 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5186. Min Act: -0.0001

Data Index: 790258 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5368. Min Act: -0.0001

Data Index: 1213438 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4198. Min Act: -0.0001

Data Index: 586805 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5259. Min Act: -0.0001

Data Index: 485491 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5090. Min Act: -0.0001

Data Index: 778856 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4726. Min Act: -0.0001

Data Index: 725556 (C4 (Web Text))

Max Activating Token Index: 606