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

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

Neuron 3615 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: 0.6266. Min Range: -0.6266

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1261615 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.6235. Min Act: -0.0000

Data Index: 698636 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4709. Min Act: -0.0000

Data Index: 3431 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4307. Min Act: -0.0000

Data Index: 743109 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4420. Min Act: -0.0000

Data Index: 14120 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1224122 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.3599. Min Act: -0.0000

Data Index: 499766 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4046. Min Act: -0.0000

Data Index: 44564 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2879. Min Act: -0.0000

Data Index: 96100 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2498. Min Act: -0.0000

Data Index: 879759 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2568. Min Act: -0.0000

Data Index: 990499 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1229 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2314. Min Act: -0.0000

Data Index: 457605 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2488. Min Act: -0.0000

Data Index: 405105 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2592. Min Act: -0.0000

Data Index: 327580 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2499. Min Act: -0.0000

Data Index: 628503 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1041464 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2593. Min Act: -0.0000

Data Index: 538738 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1084614 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.2288. Min Act: -0.0000

Data Index: 685254 (C4 (Web Text))

Max Activating Token Index: 489