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

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

Neuron 1525 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.8351. Min Act: -0.0001

Data Index: 190709 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.6841. Min Act: -0.0001

Data Index: 1047044 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.4633. Min Act: -0.0001

Data Index: 1300631 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.6423. Min Act: -0.0001

Data Index: 933776 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.5525. Min Act: -0.0000

Data Index: 366874 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.6109. Min Act: -0.0001

Data Index: 884724 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.4124. Min Act: -0.0001

Data Index: 512523 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.4824. Min Act: -0.0001

Data Index: 1002558 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.4485. Min Act: -0.0000

Data Index: 322166 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.4441. Min Act: -0.0000

Data Index: 431520 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.4469. Min Act: -0.0001

Data Index: 841757 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.2657. Min Act: -0.0001

Data Index: 809878 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.3946. Min Act: -0.0001

Data Index: 778824 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.3961. Min Act: -0.0001

Data Index: 173270 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1038189 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.3045. Min Act: -0.0001

Data Index: 611060 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.2229. Min Act: -0.0001

Data Index: 298433 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.1446. Min Act: -0.0001

Data Index: 354947 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.2544. Min Act: -0.0001

Data Index: 764595 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 1.8351. Min Range: -1.8351

Max Act: 1.3183. Min Act: -0.0001

Data Index: 1039325 (C4 (Web Text))

Max Activating Token Index: 755