Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 999 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.6250. Min Range: -8.6250

Max Act: 8.6250. Min Act: -0.0000

Data Index: 43383 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 8.6250. Min Range: -8.6250

Max Act: 8.4812. Min Act: -0.0000

Data Index: 1110020 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.9997. Min Act: -0.0000

Data Index: 1281564 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 8.6250. Min Range: -8.6250

Max Act: 7.6615. Min Act: -0.0000

Data Index: 334799 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 8.6250. Min Range: -8.6250

Max Act: 7.1289. Min Act: -0.0000

Data Index: 116112 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 8.6250. Min Range: -8.6250

Max Act: 7.0943. Min Act: -0.0000

Data Index: 270879 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.7312. Min Act: -0.0000

Data Index: 685277 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 8.6250. Min Range: -8.6250

Max Act: 7.0569. Min Act: -0.0000

Data Index: 439584 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.8726. Min Act: -0.0000

Data Index: 80242 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.9181. Min Act: -0.0000

Data Index: 1288354 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.5713. Min Act: -0.0000

Data Index: 837450 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.8927. Min Act: -0.0000

Data Index: 628070 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 8.6250. Min Range: -8.6250

Max Act: 7.0631. Min Act: -0.0000

Data Index: 116714 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.7755. Min Act: -0.0000

Data Index: 464876 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.7799. Min Act: -0.0000

Data Index: 58665 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.6905. Min Act: -0.0000

Data Index: 652720 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.8704. Min Act: -0.0000

Data Index: 1313279 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.6652. Min Act: -0.0000

Data Index: 438066 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.0799. Min Act: -0.0000

Data Index: 1227322 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 8.6250. Min Range: -8.6250

Max Act: 6.4914. Min Act: -0.0000

Data Index: 1015446 (C4 (Web Text))

Max Activating Token Index: 219