Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.9514. Min Act: -0.0000

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1360273 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7852. Min Act: -0.0000

Data Index: 453853 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1291382 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7433. Min Act: -0.0000

Data Index: 870850 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7348. Min Act: -0.0000

Data Index: 150044 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.7039. Min Act: -0.0000

Data Index: 392816 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6520. Min Act: -0.0000

Data Index: 193798 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1117475 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1311895 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6223. Min Act: -0.0000

Data Index: 54588 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1228128 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.5767. Min Act: -0.0000

Data Index: 606212 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.5909. Min Act: -0.0000

Data Index: 585041 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1184370 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1260286 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.5413. Min Act: -0.0000

Data Index: 295598 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1239696 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1123295 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.9514. Min Range: -0.9514

Max Act: 0.5681. Min Act: -0.0000

Data Index: 649506 (C4 (Web Text))

Max Activating Token Index: 611