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

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

Neuron 4616 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: 0.4164. Min Range: -0.4164

Max Act: 0.4148. Min Act: -0.0000

Data Index: 685745 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.4164. Min Act: -0.0000

Data Index: 632583 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3812. Min Act: -0.0000

Data Index: 251015 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.4010. Min Act: -0.0000

Data Index: 816473 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3670. Min Act: -0.0000

Data Index: 710448 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.4017. Min Act: -0.0000

Data Index: 581521 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1041900 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1184325 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3702. Min Act: -0.0000

Data Index: 807666 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3412. Min Act: -0.0000

Data Index: 655536 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3449. Min Act: -0.0000

Data Index: 423270 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3403. Min Act: -0.0000

Data Index: 123581 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3463. Min Act: -0.0000

Data Index: 117817 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3325. Min Act: -0.0000

Data Index: 987836 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3319. Min Act: -0.0000

Data Index: 803661 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1245598 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3120. Min Act: -0.0000

Data Index: 190372 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.2924. Min Act: -0.0000

Data Index: 695862 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1103356 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.4164. Min Range: -0.4164

Max Act: 0.3020. Min Act: -0.0000

Data Index: 558750 (C4 (Web Text))

Max Activating Token Index: 284