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

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

Neuron 582 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: 2.7160. Min Range: -2.7160

Max Act: 2.6493. Min Act: -0.0000

Data Index: 768023 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.5881. Min Act: -0.0000

Data Index: 891905 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.7160. Min Act: -0.0000

Data Index: 1357702 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.6705. Min Act: -0.0000

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.5588. Min Act: -0.0000

Data Index: 846319 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.5471. Min Act: -0.0000

Data Index: 773210 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.5223. Min Act: -0.0000

Data Index: 765614 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.4917. Min Act: -0.0000

Data Index: 138914 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.4623. Min Act: -0.0000

Data Index: 411407 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.5131. Min Act: -0.0000

Data Index: 1198803 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2933. Min Act: -0.0000

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2462. Min Act: -0.0000

Data Index: 155320 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2727. Min Act: -0.0000

Data Index: 388549 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.4532. Min Act: -0.0000

Data Index: 291653 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.3306. Min Act: -0.0000

Data Index: 26873 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.3581. Min Act: -0.0000

Data Index: 180098 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2563. Min Act: -0.0000

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.1431. Min Act: -0.0000

Data Index: 74704 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2358. Min Act: -0.0000

Data Index: 1161512 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.0216. Min Act: -0.0000

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 328