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

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

Neuron 5674 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.8032. Min Act: -0.0000

Data Index: 949913 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.8177. Min Act: -0.0000

Data Index: 190283 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7993. Min Act: -0.0000

Data Index: 759368 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1100686 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7793. Min Act: -0.0000

Data Index: 827410 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7613. Min Act: -0.0000

Data Index: 178486 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1324780 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1242193 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7371. Min Act: -0.0000

Data Index: 340957 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6296. Min Act: -0.0000

Data Index: 752338 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1011392 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1255443 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1078862 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1181902 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6661. Min Act: -0.0000

Data Index: 418730 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1026248 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1153787 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6538. Min Act: -0.0000

Data Index: 177705 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1130340 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.5745. Min Act: -0.0000

Data Index: 238741 (C4 (Web Text))

Max Activating Token Index: 587