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

Dataset: The Pile

Neuron 1880 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: 0.9550. Min Range: -0.9550

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1786887 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8617. Min Act: -0.0000

Data Index: 233217 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8312. Min Act: -0.0000

Data Index: 43061 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1688128 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1591097 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6537. Min Act: -0.0000

Data Index: 685974 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7188. Min Act: -0.0000

Data Index: 749496 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1518421 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6382. Min Act: -0.0000

Data Index: 298072 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6216. Min Act: -0.0000

Data Index: 662646 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6357. Min Act: -0.0000

Data Index: 115276 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6296. Min Act: -0.0000

Data Index: 259031 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1513758 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1910759 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1856733 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1087709 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.5686. Min Act: -0.0000

Data Index: 856052 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.5831. Min Act: -0.0000

Data Index: 280215 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.5764. Min Act: -0.0000

Data Index: 29893 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.5945. Min Act: -0.0000

Data Index: 826960 (The Pile)

Max Activating Token Index: 679