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

Dataset: The Pile

Neuron 2673 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.5583. Min Act: -0.0000

Data Index: 1169227 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.2164. Min Act: -0.0000

Data Index: 1028292 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.9010. Min Act: -0.0000

Data Index: 1601483 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.0030. Min Act: -0.0000

Data Index: 465462 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.7903. Min Act: -0.0000

Data Index: 1688142 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.7619. Min Act: -0.0000

Data Index: 1546580 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.5065. Min Act: 0.0001

Data Index: 424468 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1841482 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.5480. Min Act: 0.0001

Data Index: 1970102 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1796572 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.3943. Min Act: -0.0000

Data Index: 1577592 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1012017 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1849275 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.1238. Min Act: -0.0000

Data Index: 422847 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1753913 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1182057 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.0754. Min Act: -0.0000

Data Index: 764872 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 2.5583. Min Range: -2.5583

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1549318 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 2.5583. Min Range: -2.5583

Max Act: 0.9715. Min Act: -0.0000

Data Index: 214029 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 2.5583. Min Range: -2.5583

Max Act: 1.0074. Min Act: -0.0000

Data Index: 322919 (The Pile)

Max Activating Token Index: 375