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

Dataset: The Pile

Neuron 3695 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.4072. Min Act: -0.0000

Data Index: 649426 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.3899. Min Act: -0.0000

Data Index: 317653 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.0629. Min Act: -0.0000

Data Index: 767073 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.9904. Min Act: -0.0000

Data Index: 1596753 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.8517. Min Act: -0.0000

Data Index: 960503 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.1038. Min Act: -0.0000

Data Index: 13875 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.1023. Min Act: -0.0000

Data Index: 443474 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.1063. Min Act: -0.0000

Data Index: 802326 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.7811. Min Act: -0.0000

Data Index: 499803 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.9456. Min Act: -0.0000

Data Index: 713799 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.9339. Min Act: -0.0000

Data Index: 746701 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.0263. Min Act: -0.0000

Data Index: 8385 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.0045. Min Act: -0.0000

Data Index: 259874 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.0036. Min Act: -0.0000

Data Index: 1383002 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.9910. Min Act: -0.0000

Data Index: 960431 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.5661. Min Act: -0.0000

Data Index: 1039452 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 12.4072. Min Range: -12.4072

Max Act: 12.1559. Min Act: -0.0000

Data Index: 756451 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.7396. Min Act: -0.0000

Data Index: 418172 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.8208. Min Act: -0.0000

Data Index: 1156124 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 12.4072. Min Range: -12.4072

Max Act: 11.6988. Min Act: -0.0000

Data Index: 1970213 (The Pile)

Max Activating Token Index: 694