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

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

Neuron 836 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: 3.0830. Min Range: -3.0830

Max Act: 3.0830. Min Act: -0.0000

Data Index: 1178344 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.9230. Min Act: -0.0000

Data Index: 255508 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.8488. Min Act: -0.0000

Data Index: 197096 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.8224. Min Act: -0.0000

Data Index: 779918 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.8078. Min Act: -0.0000

Data Index: 426991 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.7779. Min Act: -0.0000

Data Index: 610576 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.9173. Min Act: -0.0000

Data Index: 436050 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.8243. Min Act: -0.0000

Data Index: 94283 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.7476. Min Act: -0.0000

Data Index: 1146149 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.5663. Min Act: -0.0000

Data Index: 234428 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.5730. Min Act: -0.0000

Data Index: 335295 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.5412. Min Act: -0.0000

Data Index: 20851 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.6133. Min Act: -0.0000

Data Index: 279998 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.5031. Min Act: -0.0000

Data Index: 614340 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4739. Min Act: -0.0000

Data Index: 31891 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.5333. Min Act: -0.0000

Data Index: 275879 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.4037. Min Act: -0.0000

Data Index: 705113 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.3630. Min Act: -0.0000

Data Index: 856118 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.3391. Min Act: -0.0000

Data Index: 590569 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 3.0830. Min Range: -3.0830

Max Act: 2.1994. Min Act: -0.0000

Data Index: 844134 (C4 (Web Text))

Max Activating Token Index: 172