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

Dataset: The Pile

Neuron 4056 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: 1.3722. Min Range: -1.3722

Max Act: 1.3722. Min Act: -0.0000

Data Index: 985106 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1038082 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1169107 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1992914 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0970. Min Act: -0.0000

Data Index: 411373 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0804. Min Act: -0.0000

Data Index: 240304 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0084. Min Act: -0.0000

Data Index: 436419 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1108070 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0834. Min Act: -0.0000

Data Index: 642846 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1180530 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9229. Min Act: 0.0000

Data Index: 195777 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1656819 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0324. Min Act: -0.0000

Data Index: 449649 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9250. Min Act: 0.0000

Data Index: 16245 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9978. Min Act: -0.0000

Data Index: 703177 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1564966 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1463870 (The Pile)

Max Activating Token Index: 912

Text #17

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.8770. Min Act: -0.0000

Data Index: 577226 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1414257 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9139. Min Act: -0.0000

Data Index: 854717 (The Pile)

Max Activating Token Index: 509