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

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

Neuron 2228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.5279. Min Act: -0.0000

Data Index: 199602 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1073604 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.4042. Min Act: -0.0000

Data Index: 245312 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1066128 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.3987. Min Act: -0.0000

Data Index: 29959 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.2503. Min Act: -0.0000

Data Index: 402338 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.2025. Min Act: -0.0000

Data Index: 714976 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.2236. Min Act: -0.0000

Data Index: 857509 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1334818 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1694. Min Act: -0.0000

Data Index: 822540 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1596. Min Act: -0.0000

Data Index: 952142 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1032146 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1686. Min Act: -0.0000

Data Index: 762107 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1308196 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1010649 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1134. Min Act: -0.0000

Data Index: 77615 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.5279. Min Range: -1.5279

Max Act: 0.9934. Min Act: -0.0000

Data Index: 740369 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1031010 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.0730. Min Act: -0.0000

Data Index: 728149 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1347134 (C4 (Web Text))

Max Activating Token Index: 488