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

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

Neuron 359 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.4217. Min Act: -0.0001

Data Index: 234033 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1220450 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3861. Min Act: -0.0001

Data Index: 431992 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3314. Min Act: -0.0001

Data Index: 161672 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3237. Min Act: -0.0001

Data Index: 449900 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3230. Min Act: -0.0001

Data Index: 833797 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3219. Min Act: -0.0001

Data Index: 1186530 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3069. Min Act: -0.0001

Data Index: 525460 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1358709 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2796. Min Act: -0.0001

Data Index: 640439 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3164. Min Act: -0.0001

Data Index: 1279757 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3173. Min Act: -0.0001

Data Index: 876098 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2846. Min Act: -0.0001

Data Index: 599194 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3035. Min Act: -0.0001

Data Index: 383243 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2928. Min Act: -0.0001

Data Index: 399848 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2704. Min Act: -0.0001

Data Index: 408884 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1354139 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1261350 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2909. Min Act: -0.0001

Data Index: 736227 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3084. Min Act: -0.0001

Data Index: 116515 (C4 (Web Text))

Max Activating Token Index: 867