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

Dataset: The Pile

Neuron 14 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1421635 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5595. Min Act: -0.0000

Data Index: 224525 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5460. Min Act: -0.0000

Data Index: 173715 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1818972 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1611887 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3937. Min Act: -0.0000

Data Index: 362588 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1307318 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1386474 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3360. Min Act: -0.0000

Data Index: 217159 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1782246 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1112489 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3413. Min Act: -0.0000

Data Index: 790817 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3594. Min Act: -0.0000

Data Index: 11940 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3402. Min Act: -0.0000

Data Index: 978656 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3509. Min Act: -0.0000

Data Index: 542097 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3515. Min Act: -0.0000

Data Index: 335657 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1255902 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3465. Min Act: -0.0000

Data Index: 276964 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1106609 (The Pile)

Max Activating Token Index: 916

Text #19

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.3422. Min Act: -0.0000

Data Index: 61187 (The Pile)

Max Activating Token Index: 364