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

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

Neuron 3854 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4928. Min Act: -0.0000

Data Index: 130459 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1030173 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3820. Min Act: -0.0000

Data Index: 350514 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3915. Min Act: 0.0000

Data Index: 1216278 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3449. Min Act: -0.0000

Data Index: 399407 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3642. Min Act: -0.0000

Data Index: 830690 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1117456 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1303218 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3280. Min Act: -0.0000

Data Index: 287724 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1255584 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3218. Min Act: -0.0000

Data Index: 139703 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3317. Min Act: -0.0000

Data Index: 886738 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3376. Min Act: -0.0000

Data Index: 209574 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3299. Min Act: -0.0000

Data Index: 836303 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3114. Min Act: -0.0000

Data Index: 44297 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3310. Min Act: 0.0000

Data Index: 316191 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1163877 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1021925 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1270869 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1167500 (C4 (Web Text))

Max Activating Token Index: 168