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

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

Neuron 5114 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.4048. Min Act: -0.0001

Data Index: 97737 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3875. Min Act: -0.0000

Data Index: 174732 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.4084. Min Act: -0.0001

Data Index: 24263 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3555. Min Act: -0.0001

Data Index: 1243136 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3905. Min Act: -0.0001

Data Index: 640806 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3463. Min Act: -0.0001

Data Index: 1319815 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3352. Min Act: -0.0001

Data Index: 90858 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3539. Min Act: -0.0001

Data Index: 389260 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3154. Min Act: -0.0001

Data Index: 344653 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3118. Min Act: -0.0001

Data Index: 892746 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2948. Min Act: -0.0001

Data Index: 838120 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3456. Min Act: -0.0001

Data Index: 776114 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3444. Min Act: -0.0000

Data Index: 742324 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3289. Min Act: -0.0001

Data Index: 911714 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3174. Min Act: -0.0000

Data Index: 870615 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3432. Min Act: -0.0001

Data Index: 160048 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3037. Min Act: -0.0001

Data Index: 775006 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3149. Min Act: -0.0001

Data Index: 933567 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3224. Min Act: -0.0001

Data Index: 472507 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1237410 (C4 (Web Text))

Max Activating Token Index: 838