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

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

Neuron 2558 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: 0.8976. Min Range: -0.8976

Max Act: 0.8976. Min Act: -0.0000

Data Index: 935567 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8929. Min Act: -0.0000

Data Index: 988629 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8365. Min Act: -0.0000

Data Index: 993871 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1356516 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7660. Min Act: -0.0000

Data Index: 409707 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7755. Min Act: -0.0000

Data Index: 338519 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1122428 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1324748 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7089. Min Act: -0.0000

Data Index: 610273 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6697. Min Act: -0.0000

Data Index: 250480 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7296. Min Act: -0.0000

Data Index: 754917 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7380. Min Act: -0.0000

Data Index: 908280 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1314131 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1117716 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1280362 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6860. Min Act: -0.0000

Data Index: 761867 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6983. Min Act: -0.0000

Data Index: 234397 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6783. Min Act: -0.0000

Data Index: 837268 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6405. Min Act: -0.0000

Data Index: 976187 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6859. Min Act: -0.0000

Data Index: 835647 (C4 (Web Text))

Max Activating Token Index: 886