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

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

Neuron 2026 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1416. Min Range: -1.1416

Max Act: 1.1416. Min Act: -0.0000

Data Index: 458026 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.1416. Min Range: -1.1416

Max Act: 1.0194. Min Act: -0.0000

Data Index: 665259 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.1416. Min Range: -1.1416

Max Act: 1.0498. Min Act: -0.0000

Data Index: 857864 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.9806. Min Act: -0.0000

Data Index: 933169 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.9325. Min Act: -0.0000

Data Index: 255468 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1000895 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.9205. Min Act: -0.0000

Data Index: 146701 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1070589 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8700. Min Act: -0.0000

Data Index: 685237 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8298. Min Act: -0.0000

Data Index: 698030 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8451. Min Act: -0.0000

Data Index: 460422 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1195483 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8103. Min Act: -0.0000

Data Index: 307394 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8262. Min Act: -0.0000

Data Index: 185644 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1068452 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8149. Min Act: -0.0000

Data Index: 580129 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1098701 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1103623 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.7582. Min Act: -0.0000

Data Index: 49452 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.1416. Min Range: -1.1416

Max Act: 0.8291. Min Act: -0.0000

Data Index: 8535 (C4 (Web Text))

Max Activating Token Index: 944