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

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

Neuron 4169 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: 0.4347. Min Range: -0.4347

Max Act: 0.4347. Min Act: -0.0000

Data Index: 632251 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4162. Min Act: -0.0000

Data Index: 907935 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4247. Min Act: -0.0000

Data Index: 809664 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3982. Min Act: -0.0000

Data Index: 323563 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4188. Min Act: -0.0000

Data Index: 11459 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4016. Min Act: -0.0000

Data Index: 163318 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4122. Min Act: -0.0000

Data Index: 509574 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3966. Min Act: -0.0000

Data Index: 975610 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3896. Min Act: -0.0001

Data Index: 1208733 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1274852 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3792. Min Act: -0.0000

Data Index: 551750 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3654. Min Act: -0.0001

Data Index: 77293 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3895. Min Act: -0.0000

Data Index: 464666 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3582. Min Act: -0.0000

Data Index: 506588 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3701. Min Act: -0.0000

Data Index: 40728 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3742. Min Act: -0.0000

Data Index: 249847 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3759. Min Act: -0.0000

Data Index: 551347 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3628. Min Act: -0.0000

Data Index: 605957 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3614. Min Act: -0.0000

Data Index: 369850 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1345038 (C4 (Web Text))

Max Activating Token Index: 58