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

Dataset: The Pile

Neuron 2964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4894. Min Range: -5.4894

Max Act: 5.4894. Min Act: -0.0000

Data Index: 241484 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 5.4894. Min Range: -5.4894

Max Act: 4.2490. Min Act: -0.0000

Data Index: 1578633 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.9534. Min Act: -0.0000

Data Index: 1457017 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 5.4894. Min Range: -5.4894

Max Act: 4.0055. Min Act: -0.0000

Data Index: 1780710 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.9759. Min Act: -0.0000

Data Index: 764268 (The Pile)

Max Activating Token Index: 35

Text #5

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.8037. Min Act: -0.0000

Data Index: 370594 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.6952. Min Act: -0.0000

Data Index: 277234 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.9824. Min Act: -0.0000

Data Index: 691693 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.9708. Min Act: -0.0000

Data Index: 773275 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.4587. Min Act: -0.0000

Data Index: 423346 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.8573. Min Act: -0.0000

Data Index: 1030268 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.7067. Min Act: -0.0000

Data Index: 1994063 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.6699. Min Act: -0.0000

Data Index: 633269 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.3187. Min Act: -0.0000

Data Index: 1665752 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.4463. Min Act: -0.0000

Data Index: 552537 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 5.4894. Min Range: -5.4894

Max Act: 4.1185. Min Act: -0.0000

Data Index: 50386 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.9077. Min Act: -0.0000

Data Index: 367984 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.5757. Min Act: -0.0000

Data Index: 1669944 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.3755. Min Act: -0.0000

Data Index: 1810047 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 5.4894. Min Range: -5.4894

Max Act: 3.3379. Min Act: -0.0000

Data Index: 899614 (The Pile)

Max Activating Token Index: 223