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

Dataset: The Pile

Neuron 4256 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: 0.6803. Min Range: -0.6803

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1122158 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.5138. Min Act: -0.0000

Data Index: 73475 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1778146 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4854. Min Act: -0.0000

Data Index: 309599 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1045006 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4321. Min Act: -0.0000

Data Index: 736953 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1608815 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4224. Min Act: -0.0000

Data Index: 992614 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1083168 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4440. Min Act: -0.0000

Data Index: 463755 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1982827 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4225. Min Act: -0.0000

Data Index: 596073 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1470980 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1444820 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3661. Min Act: -0.0000

Data Index: 42164 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1124405 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3695. Min Act: -0.0000

Data Index: 558578 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1164401 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3857. Min Act: -0.0000

Data Index: 779818 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 0.6803. Min Range: -0.6803

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1525932 (The Pile)

Max Activating Token Index: 533