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

Dataset: The Pile

Neuron 3682 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: 0.8317. Min Range: -0.8317

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1310479 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1420529 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1785905 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1704724 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6851. Min Act: -0.0000

Data Index: 252942 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6994. Min Act: -0.0000

Data Index: 782618 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6439. Min Act: -0.0000

Data Index: 913955 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.7071. Min Act: -0.0000

Data Index: 183432 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1494002 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6662. Min Act: -0.0000

Data Index: 352919 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6173. Min Act: -0.0000

Data Index: 113224 (The Pile)

Max Activating Token Index: 111

Text #11

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1679149 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1781518 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1576318 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1419223 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6662. Min Act: -0.0000

Data Index: 251723 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.5976. Min Act: -0.0000

Data Index: 389905 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6593. Min Act: -0.0000

Data Index: 716987 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1513750 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.8317. Min Range: -0.8317

Max Act: 0.6321. Min Act: -0.0000

Data Index: 140783 (The Pile)

Max Activating Token Index: 198