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

Dataset: The Pile

Neuron 3427 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1128944 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4343. Min Act: -0.0000

Data Index: 404731 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4211. Min Act: -0.0000

Data Index: 708999 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4132. Min Act: -0.0000

Data Index: 756788 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3944. Min Act: -0.0000

Data Index: 503822 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1708903 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1297635 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1880024 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1699185 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3770. Min Act: -0.0000

Data Index: 800820 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1801952 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1246524 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3809. Min Act: -0.0000

Data Index: 580463 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4306. Min Act: -0.0000

Data Index: 797748 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1138978 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1762284 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3879. Min Act: -0.0000

Data Index: 580401 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1692327 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1554944 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1393173 (The Pile)

Max Activating Token Index: 467