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

Dataset: The Pile

Neuron 2312 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1452439 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6367. Min Act: -0.0000

Data Index: 409991 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1611995 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1551909 (The Pile)

Max Activating Token Index: 747

Text #4

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6390. Min Act: -0.0000

Data Index: 581538 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6555. Min Act: -0.0000

Data Index: 289717 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1805706 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1057367 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5462. Min Act: -0.0000

Data Index: 166832 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1129016 (The Pile)

Max Activating Token Index: 544

Text #10

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1362051 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5453. Min Act: -0.0000

Data Index: 894399 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1251447 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1963669 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1876572 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4847. Min Act: -0.0000

Data Index: 549638 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4858. Min Act: -0.0000

Data Index: 100680 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1589164 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1608901 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.4847. Min Act: -0.0000

Data Index: 623712 (The Pile)

Max Activating Token Index: 83