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

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

Neuron 4550 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: 1.9098. Min Range: -1.9098

Max Act: 1.9098. Min Act: -0.0000

Data Index: 818986 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.8128. Min Act: -0.0000

Data Index: 502722 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.6213. Min Act: -0.0000

Data Index: 86517 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.5355. Min Act: -0.0000

Data Index: 816425 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.5109. Min Act: -0.0000

Data Index: 727392 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.5524. Min Act: -0.0000

Data Index: 1334420 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.5782. Min Act: -0.0000

Data Index: 752238 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.4638. Min Act: -0.0000

Data Index: 1084193 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.5364. Min Act: -0.0000

Data Index: 813375 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.4577. Min Act: -0.0000

Data Index: 40337 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.4836. Min Act: -0.0000

Data Index: 743999 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1072276 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1316575 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.4479. Min Act: -0.0000

Data Index: 29218 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.4755. Min Act: -0.0000

Data Index: 515169 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.4376. Min Act: -0.0000

Data Index: 1164220 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.3899. Min Act: -0.0000

Data Index: 590923 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.2752. Min Act: -0.0000

Data Index: 70991 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.3098. Min Act: -0.0000

Data Index: 379177 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.9098. Min Range: -1.9098

Max Act: 1.3154. Min Act: -0.0000

Data Index: 354905 (C4 (Web Text))

Max Activating Token Index: 922