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

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

Neuron 5991 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: 3.5346. Min Range: -3.5346

Max Act: 3.5346. Min Act: -0.0000

Data Index: 725085 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4128. Min Act: -0.0000

Data Index: 752292 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3714. Min Act: -0.0000

Data Index: 1081449 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.0821. Min Act: -0.0000

Data Index: 769932 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3591. Min Act: -0.0000

Data Index: 1266242 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.0162. Min Act: -0.0000

Data Index: 120845 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.0534. Min Act: -0.0000

Data Index: 922453 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.9315. Min Act: -0.0000

Data Index: 1084010 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.9315. Min Act: -0.0000

Data Index: 354463 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.7844. Min Act: -0.0000

Data Index: 1263570 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.7603. Min Act: -0.0000

Data Index: 564422 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.7297. Min Act: -0.0000

Data Index: 439894 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.7163. Min Act: -0.0000

Data Index: 988355 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.7034. Min Act: -0.0000

Data Index: 491861 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.6326. Min Act: -0.0000

Data Index: 1246207 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.8493. Min Act: -0.0000

Data Index: 686537 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.7162. Min Act: -0.0000

Data Index: 921181 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.7041. Min Act: -0.0000

Data Index: 108178 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.8236. Min Act: -0.0000

Data Index: 610814 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.5346. Min Range: -3.5346

Max Act: 2.6799. Min Act: -0.0000

Data Index: 543334 (C4 (Web Text))

Max Activating Token Index: 369