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

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

Neuron 1053 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.4602. Min Range: -8.4602

Max Act: 8.4602. Min Act: -0.0000

Data Index: 363762 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 8.4602. Min Range: -8.4602

Max Act: 8.3736. Min Act: -0.0000

Data Index: 687861 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 8.4602. Min Range: -8.4602

Max Act: 8.2310. Min Act: -0.0000

Data Index: 1043647 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.7278. Min Act: -0.0000

Data Index: 363961 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 8.4602. Min Range: -8.4602

Max Act: 8.0939. Min Act: -0.0000

Data Index: 107695 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.5443. Min Act: -0.0000

Data Index: 1356607 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.6429. Min Act: -0.0000

Data Index: 80684 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.6114. Min Act: -0.0000

Data Index: 545339 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.0379. Min Act: -0.0000

Data Index: 100429 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.1233. Min Act: -0.0000

Data Index: 548854 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.2157. Min Act: -0.0000

Data Index: 527699 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.6552. Min Act: -0.0000

Data Index: 921281 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 8.4602. Min Range: -8.4602

Max Act: 7.0113. Min Act: -0.0000

Data Index: 1010618 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.7311. Min Act: -0.0000

Data Index: 353707 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.7289. Min Act: -0.0000

Data Index: 416772 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.4899. Min Act: -0.0000

Data Index: 418786 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.4863. Min Act: -0.0000

Data Index: 121666 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.4542. Min Act: -0.0000

Data Index: 636930 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.6199. Min Act: -0.0000

Data Index: 1341902 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 8.4602. Min Range: -8.4602

Max Act: 6.2172. Min Act: -0.0000

Data Index: 386338 (C4 (Web Text))

Max Activating Token Index: 102