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

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

Neuron 362 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: 0.4715. Min Range: -0.4715

Max Act: 0.3927. Min Act: -0.0000

Data Index: 436127 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1181734 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4239. Min Act: -0.0000

Data Index: 603184 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1017158 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1069168 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3523. Min Act: -0.0000

Data Index: 804018 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3998. Min Act: -0.0000

Data Index: 556023 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1319912 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1059502 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3487. Min Act: -0.0000

Data Index: 634089 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1116622 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3267. Min Act: -0.0000

Data Index: 274098 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3453. Min Act: -0.0000

Data Index: 991831 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3266. Min Act: -0.0000

Data Index: 695297 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3548. Min Act: -0.0000

Data Index: 771504 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3275. Min Act: -0.0000

Data Index: 318841 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3312. Min Act: -0.0000

Data Index: 104005 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3021. Min Act: -0.0000

Data Index: 756548 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3356. Min Act: -0.0000

Data Index: 188802 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3166. Min Act: -0.0000

Data Index: 788253 (C4 (Web Text))

Max Activating Token Index: 420