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

Dataset: The Pile

Neuron 2213 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: 0.5133. Min Range: -0.5133

Max Act: 0.5133. Min Act: -0.0000

Data Index: 825041 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1336789 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1174479 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1541313 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1497313 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4214. Min Act: -0.0000

Data Index: 907358 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1082744 (The Pile)

Max Activating Token Index: 659

Text #7

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1695431 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.4280. Min Act: -0.0000

Data Index: 502676 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1970611 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3621. Min Act: -0.0000

Data Index: 931052 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3515. Min Act: -0.0000

Data Index: 389107 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3288. Min Act: -0.0000

Data Index: 531157 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3694. Min Act: -0.0000

Data Index: 167516 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1082385 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1405056 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3169. Min Act: 0.0000

Data Index: 1134545 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1251114 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.3149. Min Act: -0.0000

Data Index: 474545 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 0.5133. Min Range: -0.5133

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1844959 (The Pile)

Max Activating Token Index: 457