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

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

Neuron 2370 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.6897. Min Act: -0.0001

Data Index: 223732 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.6221. Min Act: -0.0001

Data Index: 1257448 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.5358. Min Act: -0.0001

Data Index: 1148913 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.6575. Min Act: -0.0000

Data Index: 1098988 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.6360. Min Act: -0.0001

Data Index: 854972 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1073453 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.5097. Min Act: -0.0000

Data Index: 475144 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3968. Min Act: -0.0001

Data Index: 292859 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3946. Min Act: -0.0001

Data Index: 269867 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3084. Min Act: -0.0001

Data Index: 199577 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.4513. Min Act: -0.0000

Data Index: 1132283 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.4968. Min Act: -0.0001

Data Index: 826877 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3888. Min Act: -0.0001

Data Index: 206238 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3639. Min Act: -0.0001

Data Index: 661047 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3294. Min Act: -0.0001

Data Index: 367857 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.4189. Min Act: -0.0001

Data Index: 313880 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3774. Min Act: -0.0001

Data Index: 863414 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1207405 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.2296. Min Act: -0.0001

Data Index: 1119551 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 1.6897. Min Range: -1.6897

Max Act: 1.2304. Min Act: -0.0001

Data Index: 789875 (C4 (Web Text))

Max Activating Token Index: 460