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

Dataset: The Pile

Neuron 4062 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.9087. Min Act: 0.0000

Data Index: 670601 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1068100 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1244060 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8674. Min Act: -0.0000

Data Index: 823100 (The Pile)

Max Activating Token Index: 137

Text #4

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8286. Min Act: -0.0000

Data Index: 508416 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1091496 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7720. Min Act: -0.0000

Data Index: 478279 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7226. Min Act: -0.0000

Data Index: 701843 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1364082 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7353. Min Act: -0.0000

Data Index: 542673 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1637428 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1771934 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6898. Min Act: -0.0000

Data Index: 438532 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6893. Min Act: -0.0000

Data Index: 906730 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6435. Min Act: -0.0000

Data Index: 301035 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6491. Min Act: -0.0000

Data Index: 661792 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6372. Min Act: -0.0000

Data Index: 433230 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6797. Min Act: -0.0000

Data Index: 216932 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6735. Min Act: -0.0000

Data Index: 184972 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6511. Min Act: -0.0000

Data Index: 394955 (The Pile)

Max Activating Token Index: 17