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

Dataset: The Pile

Neuron 3285 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0831. Min Act: -0.0000

Data Index: 75505 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1826913 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0578. Min Act: -0.0000

Data Index: 851575 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0660. Min Act: -0.0000

Data Index: 152772 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1543270 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9149. Min Act: -0.0000

Data Index: 768135 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9667. Min Act: -0.0000

Data Index: 889745 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8949. Min Act: -0.0000

Data Index: 746146 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.0381. Min Act: -0.0000

Data Index: 280470 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8994. Min Act: -0.0000

Data Index: 774543 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1324074 (The Pile)

Max Activating Token Index: 797

Text #11

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1749763 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1739512 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8194. Min Act: -0.0000

Data Index: 340165 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8497. Min Act: -0.0000

Data Index: 133244 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1591329 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1048613 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1958430 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8758. Min Act: -0.0000

Data Index: 500728 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1038376 (The Pile)

Max Activating Token Index: 119