Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3558 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1014047 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3763. Min Act: -0.0001

Data Index: 923686 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3551. Min Act: -0.0001

Data Index: 333348 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3393. Min Act: -0.0001

Data Index: 249991 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3475. Min Act: -0.0001

Data Index: 1333642 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3335. Min Act: -0.0001

Data Index: 196633 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3428. Min Act: -0.0001

Data Index: 1279071 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3628. Min Act: -0.0001

Data Index: 941843 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3274. Min Act: -0.0001

Data Index: 179008 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3336. Min Act: -0.0001

Data Index: 750227 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3168. Min Act: -0.0001

Data Index: 129637 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3161. Min Act: -0.0001

Data Index: 534810 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3354. Min Act: -0.0001

Data Index: 620524 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3451. Min Act: -0.0001

Data Index: 373840 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3267. Min Act: -0.0000

Data Index: 782338 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3217. Min Act: -0.0001

Data Index: 778049 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2992. Min Act: -0.0000

Data Index: 138908 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1042293 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1262447 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3172. Min Act: -0.0001

Data Index: 890391 (C4 (Web Text))

Max Activating Token Index: 939