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

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

Neuron 3674 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9856. Min Act: -0.0000

Data Index: 428861 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9627. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8893. Min Act: -0.0000

Data Index: 986844 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1183563 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1212176 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.7263. Min Act: 0.0000

Data Index: 1226674 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.7519. Min Act: -0.0000

Data Index: 90698 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.7158. Min Act: 0.0000

Data Index: 923605 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.7082. Min Act: -0.0000

Data Index: 585656 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1188800 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6682. Min Act: -0.0000

Data Index: 234631 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6618. Min Act: -0.0000

Data Index: 232285 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6570. Min Act: 0.0000

Data Index: 712203 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6630. Min Act: -0.0000

Data Index: 852294 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6378. Min Act: -0.0000

Data Index: 137365 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1275021 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6359. Min Act: -0.0000

Data Index: 794927 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6217. Min Act: -0.0000

Data Index: 489814 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.6178. Min Act: -0.0000

Data Index: 751851 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.5786. Min Act: -0.0000

Data Index: 57022 (C4 (Web Text))

Max Activating Token Index: 891