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

Dataset: The Pile

Neuron 4496 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.6541. Min Act: -0.0000

Data Index: 717630 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.5294. Min Act: -0.0000

Data Index: 551096 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.6239. Min Act: -0.0000

Data Index: 1960372 (The Pile)

Max Activating Token Index: 830

Text #3

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1620771 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.6213. Min Act: -0.0000

Data Index: 87253 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.4137. Min Act: -0.0000

Data Index: 1823321 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1608946 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1432858 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1146563 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.2528. Min Act: -0.0000

Data Index: 122330 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3956. Min Act: -0.0000

Data Index: 704414 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3852. Min Act: -0.0000

Data Index: 942779 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3129. Min Act: -0.0000

Data Index: 612421 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.2484. Min Act: -0.0000

Data Index: 920652 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3725. Min Act: -0.0000

Data Index: 889974 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1611056 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3476. Min Act: -0.0000

Data Index: 293825 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1981791 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1891407 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 1.6541. Min Range: -1.6541

Max Act: 1.3418. Min Act: -0.0000

Data Index: 763214 (The Pile)

Max Activating Token Index: 109