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

Dataset: The Pile

Neuron 1613 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: 1.1672. Min Range: -1.1672

Max Act: 1.1672. Min Act: -0.0000

Data Index: 819512 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1578048 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9921. Min Act: -0.0000

Data Index: 742683 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9770. Min Act: -0.0000

Data Index: 766781 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0522. Min Act: -0.0000

Data Index: 656215 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1637678 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9347. Min Act: -0.0000

Data Index: 749991 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9835. Min Act: -0.0000

Data Index: 351141 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1167883 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9792. Min Act: -0.0000

Data Index: 37722 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1415584 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8882. Min Act: -0.0000

Data Index: 317181 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1698246 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8698. Min Act: -0.0000

Data Index: 837656 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8354. Min Act: -0.0000

Data Index: 227055 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1164394 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8173. Min Act: -0.0000

Data Index: 117475 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8678. Min Act: -0.0000

Data Index: 296413 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9215. Min Act: -0.0000

Data Index: 210000 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1665193 (The Pile)

Max Activating Token Index: 756