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

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

Neuron 1572 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: 1.5378. Min Range: -1.5378

Max Act: 1.4560. Min Act: -0.0000

Data Index: 436402 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.2784. Min Act: -0.0000

Data Index: 727702 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.2279. Min Act: -0.0000

Data Index: 533502 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.5378. Min Act: -0.0000

Data Index: 690914 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.2630. Min Act: -0.0000

Data Index: 292299 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.1814. Min Act: -0.0000

Data Index: 55453 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.0138. Min Act: -0.0000

Data Index: 121048 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.2042. Min Act: -0.0000

Data Index: 833893 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1174583 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.0513. Min Act: -0.0000

Data Index: 797164 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1210834 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.1142. Min Act: -0.0000

Data Index: 210715 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.1499. Min Act: -0.0000

Data Index: 69413 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.0307. Min Act: -0.0000

Data Index: 539268 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.5378. Min Range: -1.5378

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1319111 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.5378. Min Range: -1.5378

Max Act: 0.7317. Min Act: -0.0000

Data Index: 470869 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.5378. Min Range: -1.5378

Max Act: 1.0067. Min Act: -0.0000

Data Index: 972376 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 1.5378. Min Range: -1.5378

Max Act: 0.9358. Min Act: -0.0000

Data Index: 496798 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.5378. Min Range: -1.5378

Max Act: 0.9775. Min Act: -0.0000

Data Index: 4240 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.5378. Min Range: -1.5378

Max Act: 0.9783. Min Act: -0.0000

Data Index: 696537 (C4 (Web Text))

Max Activating Token Index: 485