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

Dataset: The Pile

Neuron 653 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: 3.6587. Min Range: -3.6587

Max Act: 3.3498. Min Act: -0.0000

Data Index: 1258776 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.3568. Min Act: -0.0000

Data Index: 1474402 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.1767. Min Act: -0.0000

Data Index: 954715 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.6587. Min Act: -0.0000

Data Index: 1904919 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.2047. Min Act: -0.0000

Data Index: 1672906 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.5049. Min Act: -0.0000

Data Index: 183572 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.4058. Min Act: -0.0000

Data Index: 1734319 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.1462. Min Act: -0.0000

Data Index: 1901606 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.1070. Min Act: -0.0000

Data Index: 459593 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.6574. Min Act: -0.0000

Data Index: 1145365 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 3.6587. Min Range: -3.6587

Max Act: 2.7989. Min Act: -0.0000

Data Index: 1032241 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.2929. Min Act: -0.0000

Data Index: 761381 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 3.6587. Min Range: -3.6587

Max Act: 2.9807. Min Act: -0.0000

Data Index: 213049 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.0636. Min Act: -0.0000

Data Index: 1150583 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 3.6587. Min Range: -3.6587

Max Act: 2.9240. Min Act: -0.0000

Data Index: 513438 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 3.6587. Min Range: -3.6587

Max Act: 2.9548. Min Act: -0.0000

Data Index: 935104 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 3.6587. Min Range: -3.6587

Max Act: 2.5468. Min Act: -0.0000

Data Index: 1587520 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.0740. Min Act: -0.0000

Data Index: 1397399 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 3.6587. Min Range: -3.6587

Max Act: 2.7611. Min Act: -0.0000

Data Index: 637018 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 3.6587. Min Range: -3.6587

Max Act: 3.0035. Min Act: -0.0000

Data Index: 1872486 (The Pile)

Max Activating Token Index: 560