Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2500 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1282. Min Range: -1.1282

Max Act: 1.1282. Min Act: -0.0000

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9661. Min Act: -0.0000

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.1282. Min Range: -1.1282

Max Act: 1.0021. Min Act: -0.0000

Data Index: 174725 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9966. Min Act: -0.0000

Data Index: 780561 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8920. Min Act: -0.0000

Data Index: 213403 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8423. Min Act: -0.0000

Data Index: 254517 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9982. Min Act: -0.0000

Data Index: 214051 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8732. Min Act: -0.0000

Data Index: 937727 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8173. Min Act: -0.0000

Data Index: 503377 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8624. Min Act: -0.0000

Data Index: 400213 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7752. Min Act: -0.0000

Data Index: 614183 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7927. Min Act: -0.0000

Data Index: 588299 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7870. Min Act: -0.0000

Data Index: 627607 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8151. Min Act: 0.0000

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7989. Min Act: -0.0000

Data Index: 208679 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9118. Min Act: -0.0000

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7618. Min Act: -0.0000

Data Index: 611418 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7906. Min Act: -0.0000

Data Index: 36814 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1242628 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7563. Min Act: -0.0000

Data Index: 109309 (C4 (Web Text))

Max Activating Token Index: 685