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

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

Neuron 1801 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0668. Min Range: -1.0668

Max Act: 1.0668. Min Act: -0.0000

Data Index: 510736 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8858. Min Act: -0.0000

Data Index: 718697 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7297. Min Act: -0.0000

Data Index: 286061 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7193. Min Act: -0.0000

Data Index: 745460 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.7066. Min Act: -0.0000

Data Index: 494890 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6735. Min Act: -0.0000

Data Index: 116385 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6660. Min Act: -0.0000

Data Index: 316904 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1246338 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6742. Min Act: -0.0000

Data Index: 537040 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1295057 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.5623. Min Act: -0.0000

Data Index: 999888 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1027443 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.5864. Min Act: -0.0000

Data Index: 908876 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1320539 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.5883. Min Act: -0.0000

Data Index: 927939 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6072. Min Act: -0.0000

Data Index: 111207 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.5983. Min Act: -0.0000

Data Index: 310280 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6150. Min Act: -0.0000

Data Index: 577359 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.6125. Min Act: -0.0000

Data Index: 131124 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1172408 (C4 (Web Text))

Max Activating Token Index: 21