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

Dataset: The Pile

Neuron 1917 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7734. Min Act: -0.0000

Data Index: 531474 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1617624 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1258807 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1692077 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6433. Min Act: -0.0000

Data Index: 365214 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5741. Min Act: 0.0000

Data Index: 351888 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1935754 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1858507 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1052699 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1525671 (The Pile)

Max Activating Token Index: 654

Text #10

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5107. Min Act: -0.0000

Data Index: 268808 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5425. Min Act: -0.0000

Data Index: 682820 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4861. Min Act: -0.0000

Data Index: 407182 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4966. Min Act: -0.0000

Data Index: 47285 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5117. Min Act: -0.0000

Data Index: 595593 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5291. Min Act: -0.0000

Data Index: 786763 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1635067 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5228. Min Act: -0.0000

Data Index: 340394 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5042. Min Act: -0.0000

Data Index: 116018 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4676. Min Act: -0.0000

Data Index: 306118 (The Pile)

Max Activating Token Index: 685