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

Dataset: The Pile

Neuron 2464 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: 1.8722. Min Range: -1.8722

Max Act: 1.7784. Min Act: -0.0000

Data Index: 1387420 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8684. Min Act: -0.0000

Data Index: 1550366 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8373. Min Act: -0.0000

Data Index: 197549 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6949. Min Act: -0.0000

Data Index: 488262 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8722. Min Act: -0.0000

Data Index: 1866561 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7703. Min Act: -0.0000

Data Index: 1692094 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7656. Min Act: -0.0000

Data Index: 410185 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6588. Min Act: -0.0000

Data Index: 1059947 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7390. Min Act: -0.0000

Data Index: 1711727 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5211. Min Act: -0.0000

Data Index: 330279 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1013589 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1368607 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1106968 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7300. Min Act: -0.0000

Data Index: 658666 (The Pile)

Max Activating Token Index: 192

Text #14

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1512063 (The Pile)

Max Activating Token Index: 85

Text #15

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1021041 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1639358 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1643228 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5774. Min Act: -0.0000

Data Index: 776105 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5596. Min Act: -0.0000

Data Index: 1671251 (The Pile)

Max Activating Token Index: 699