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

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

Neuron 4190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.6011. Min Act: -0.0000

Data Index: 31781 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.7035. Min Act: -0.0000

Data Index: 367147 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.7451. Min Act: -0.0000

Data Index: 815125 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.8185. Min Act: -0.0000

Data Index: 85397 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.5915. Min Act: -0.0000

Data Index: 398863 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.7645. Min Act: -0.0000

Data Index: 424535 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1051341 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.7204. Min Act: -0.0000

Data Index: 429369 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.5624. Min Act: -0.0000

Data Index: 96928 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.6713. Min Act: -0.0000

Data Index: 37584 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.6678. Min Act: -0.0000

Data Index: 186729 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.8916. Min Act: -0.0000

Data Index: 1248509 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.5404. Min Act: -0.0000

Data Index: 749363 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.4816. Min Act: -0.0000

Data Index: 375877 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.3297. Min Act: -0.0000

Data Index: 415975 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.4364. Min Act: -0.0000

Data Index: 383595 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1003660 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.4198. Min Act: -0.0000

Data Index: 182911 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.2041. Min Act: -0.0000

Data Index: 602343 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 1.8916. Min Range: -1.8916

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1099172 (C4 (Web Text))

Max Activating Token Index: 142