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

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

Neuron 4508 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: 0.8316. Min Range: -0.8316

Max Act: 0.7772. Min Act: -0.0000

Data Index: 953948 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1171969 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7246. Min Act: -0.0000

Data Index: 787761 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1209747 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7295. Min Act: -0.0000

Data Index: 582847 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7288. Min Act: 0.0001

Data Index: 471183 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6844. Min Act: -0.0000

Data Index: 736042 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6356. Min Act: -0.0000

Data Index: 803245 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7008. Min Act: 0.0000

Data Index: 425763 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7121. Min Act: -0.0000

Data Index: 213719 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7080. Min Act: -0.0000

Data Index: 365883 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1129517 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6357. Min Act: -0.0000

Data Index: 217145 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6404. Min Act: -0.0000

Data Index: 498772 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6306. Min Act: -0.0000

Data Index: 776885 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6434. Min Act: -0.0000

Data Index: 335695 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6247. Min Act: -0.0000

Data Index: 785393 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1087484 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6236. Min Act: -0.0000

Data Index: 158788 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.3820. Min Act: -0.0000

Data Index: 845091 (C4 (Web Text))

Max Activating Token Index: 240