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

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

Neuron 3507 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: 1.7728. Min Range: -1.7728

Max Act: 1.6236. Min Act: -0.0000

Data Index: 1120343 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.7728. Min Act: -0.0000

Data Index: 18888 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.6675. Min Act: -0.0000

Data Index: 123215 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.6336. Min Act: -0.0000

Data Index: 233770 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.7301. Min Act: -0.0000

Data Index: 1060659 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.6362. Min Act: -0.0000

Data Index: 90418 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1252713 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3556. Min Act: -0.0000

Data Index: 950152 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1197205 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3008. Min Act: -0.0000

Data Index: 296548 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3714. Min Act: -0.0000

Data Index: 130616 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3676. Min Act: -0.0000

Data Index: 820954 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3631. Min Act: -0.0000

Data Index: 796454 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3289. Min Act: -0.0000

Data Index: 11079 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3175. Min Act: -0.0000

Data Index: 134776 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1095798 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.3237. Min Act: -0.0000

Data Index: 789160 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.2447. Min Act: -0.0000

Data Index: 370147 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.2176. Min Act: -0.0000

Data Index: 745878 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.7728. Min Range: -1.7728

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1333932 (C4 (Web Text))

Max Activating Token Index: 604