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

Dataset: The Pile

Neuron 2318 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0000

Data Index: 579792 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1548840 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1169774 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6442. Min Act: -0.0000

Data Index: 134908 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1138779 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5728. Min Act: 0.0000

Data Index: 1101545 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5924. Min Act: -0.0000

Data Index: 169979 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5562. Min Act: -0.0000

Data Index: 892313 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5710. Min Act: -0.0000

Data Index: 248532 (The Pile)

Max Activating Token Index: 432

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1018331 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5785. Min Act: 0.0000

Data Index: 87000 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1739790 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5548. Min Act: 0.0000

Data Index: 1667137 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5554. Min Act: 0.0000

Data Index: 982908 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1392444 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5560. Min Act: -0.0000

Data Index: 165597 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5318. Min Act: -0.0000

Data Index: 353197 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5164. Min Act: -0.0000

Data Index: 695442 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1995687 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5074. Min Act: -0.0000

Data Index: 49553 (The Pile)

Max Activating Token Index: 32