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

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

Neuron 4067 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4377. Min Act: 0.0000

Data Index: 570349 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4072. Min Act: -0.0000

Data Index: 690681 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3946. Min Act: -0.0000

Data Index: 84524 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3885. Min Act: -0.0000

Data Index: 897773 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3829. Min Act: -0.0000

Data Index: 707762 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3774. Min Act: -0.0000

Data Index: 500800 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1065018 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3773. Min Act: -0.0000

Data Index: 479614 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3481. Min Act: -0.0000

Data Index: 944664 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1350471 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1242644 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3352. Min Act: -0.0000

Data Index: 62841 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1091970 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1119507 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3467. Min Act: -0.0000

Data Index: 396943 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1169651 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3194. Min Act: -0.0000

Data Index: 604282 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3075. Min Act: -0.0000

Data Index: 255070 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3276. Min Act: -0.0000

Data Index: 284347 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3153. Min Act: -0.0000

Data Index: 847977 (C4 (Web Text))

Max Activating Token Index: 799