Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4387 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1318. Min Range: -1.1318

Max Act: 1.1318. Min Act: -0.0000

Data Index: 284437 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 1.1318. Min Range: -1.1318

Max Act: 1.1219. Min Act: -0.0000

Data Index: 278775 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.1318. Min Range: -1.1318

Max Act: 1.0650. Min Act: -0.0000

Data Index: 287595 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 1.1318. Min Range: -1.1318

Max Act: 1.0405. Min Act: -0.0000

Data Index: 602368 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9740. Min Act: -0.0000

Data Index: 228158 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9917. Min Act: -0.0000

Data Index: 851633 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9881. Min Act: 0.0000

Data Index: 324916 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1108260 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1053773 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1273665 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9735. Min Act: -0.0000

Data Index: 74130 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9029. Min Act: -0.0000

Data Index: 239382 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1319927 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.9228. Min Act: 0.0000

Data Index: 609671 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.8932. Min Act: -0.0000

Data Index: 306688 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.8626. Min Act: 0.0000

Data Index: 164060 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.8604. Min Act: -0.0000

Data Index: 943540 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.8867. Min Act: -0.0000

Data Index: 893648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1012709 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.1318. Min Range: -1.1318

Max Act: 0.8879. Min Act: -0.0000

Data Index: 449348 (C4 (Web Text))

Max Activating Token Index: 317