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

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

Neuron 3263 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: 1.2189. Min Range: -1.2189

Max Act: 1.2189. Min Act: -0.0001

Data Index: 1295600 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 1.2189. Min Range: -1.2189

Max Act: 1.2109. Min Act: -0.0001

Data Index: 1022620 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.2189. Min Range: -1.2189

Max Act: 1.0060. Min Act: -0.0001

Data Index: 38400 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7539. Min Act: -0.0000

Data Index: 941518 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7764. Min Act: -0.0001

Data Index: 848006 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7909. Min Act: -0.0000

Data Index: 871352 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7265. Min Act: -0.0001

Data Index: 1352552 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7605. Min Act: -0.0001

Data Index: 981904 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7818. Min Act: -0.0000

Data Index: 19268 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7283. Min Act: -0.0000

Data Index: 394387 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1161351 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7775. Min Act: -0.0000

Data Index: 23018 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7229. Min Act: -0.0001

Data Index: 1336854 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7202. Min Act: -0.0000

Data Index: 131993 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.7938. Min Act: -0.0001

Data Index: 114866 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.6534. Min Act: -0.0001

Data Index: 29753 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.6996. Min Act: -0.0001

Data Index: 677589 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1223268 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.6400. Min Act: -0.0001

Data Index: 1122811 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.2189. Min Range: -1.2189

Max Act: 0.6793. Min Act: -0.0000

Data Index: 817605 (C4 (Web Text))

Max Activating Token Index: 975