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

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

Neuron 582 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: 0.5131. Min Range: -0.5131

Max Act: 0.5131. Min Act: -0.0000

Data Index: 427456 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3662. Min Act: -0.0000

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3777. Min Act: -0.0000

Data Index: 503633 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3605. Min Act: -0.0000

Data Index: 862820 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3562. Min Act: -0.0000

Data Index: 856466 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1317628 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3453. Min Act: -0.0000

Data Index: 773825 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1274069 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3400. Min Act: -0.0000

Data Index: 351426 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3486. Min Act: -0.0000

Data Index: 714020 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3648. Min Act: -0.0000

Data Index: 632699 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1214437 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3543. Min Act: -0.0000

Data Index: 936879 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3429. Min Act: -0.0000

Data Index: 945827 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1168203 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3240. Min Act: -0.0000

Data Index: 792620 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3176. Min Act: -0.0000

Data Index: 785158 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3194. Min Act: -0.0000

Data Index: 544580 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3204. Min Act: -0.0000

Data Index: 928900 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1083966 (C4 (Web Text))

Max Activating Token Index: 622