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

Dataset: The Pile

Neuron 5065 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: 0.8448. Min Range: -0.8448

Max Act: 0.8133. Min Act: -0.0000

Data Index: 503828 (The Pile)

Max Activating Token Index: 921

Text #1

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1331578 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1859333 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1344235 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1857128 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7359. Min Act: -0.0000

Data Index: 876709 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1464007 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7170. Min Act: -0.0000

Data Index: 18487 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1318056 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6207. Min Act: -0.0000

Data Index: 675272 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5952. Min Act: -0.0000

Data Index: 116351 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5152. Min Act: -0.0000

Data Index: 219387 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4978. Min Act: -0.0000

Data Index: 466447 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5678. Min Act: -0.0000

Data Index: 596899 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6321. Min Act: -0.0000

Data Index: 743028 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1854946 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6202. Min Act: -0.0000

Data Index: 783344 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1622642 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1614623 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7590. Min Act: -0.0000

Data Index: 601803 (The Pile)

Max Activating Token Index: 903