Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3571 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0343. Min Range: -1.0343

Max Act: 1.0129. Min Act: -0.0001

Data Index: 543306 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 1.0343. Min Range: -1.0343

Max Act: 1.0343. Min Act: -0.0001

Data Index: 1222364 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9383. Min Act: -0.0001

Data Index: 216164 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9260. Min Act: -0.0001

Data Index: 958386 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8693. Min Act: -0.0001

Data Index: 1355309 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8924. Min Act: -0.0001

Data Index: 848419 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9157. Min Act: -0.0001

Data Index: 692587 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7485. Min Act: -0.0001

Data Index: 323156 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8711. Min Act: -0.0001

Data Index: 71186 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7897. Min Act: -0.0001

Data Index: 1139189 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7401. Min Act: -0.0001

Data Index: 182828 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7440. Min Act: -0.0001

Data Index: 24406 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7793. Min Act: -0.0001

Data Index: 1266147 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7812. Min Act: -0.0001

Data Index: 1067402 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.6935. Min Act: -0.0001

Data Index: 1275659 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8170. Min Act: -0.0001

Data Index: 1037493 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7340. Min Act: -0.0001

Data Index: 561628 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.6769. Min Act: -0.0001

Data Index: 40780 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.6610. Min Act: -0.0001

Data Index: 370021 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.6339. Min Act: -0.0001

Data Index: 320969 (C4 (Web Text))

Max Activating Token Index: 87