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

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

Neuron 3810 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: 1.7844. Min Range: -1.7844

Max Act: 1.7544. Min Act: -0.0000

Data Index: 808645 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.7844. Min Act: -0.0000

Data Index: 780474 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1128451 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4814. Min Act: -0.0000

Data Index: 941950 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4514. Min Act: -0.0000

Data Index: 479713 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5126. Min Act: -0.0000

Data Index: 672763 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.3392. Min Act: -0.0000

Data Index: 155627 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4296. Min Act: -0.0000

Data Index: 820656 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4021. Min Act: -0.0000

Data Index: 932012 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4669. Min Act: -0.0000

Data Index: 577322 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1313267 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1323202 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2269. Min Act: -0.0000

Data Index: 33328 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2767. Min Act: -0.0000

Data Index: 614493 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2820. Min Act: -0.0000

Data Index: 313200 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2551. Min Act: -0.0000

Data Index: 125262 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2494. Min Act: -0.0000

Data Index: 408083 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2968. Min Act: -0.0000

Data Index: 964016 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2188. Min Act: -0.0000

Data Index: 864312 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.2119. Min Act: -0.0000

Data Index: 888887 (C4 (Web Text))

Max Activating Token Index: 771