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

Dataset: The Pile

Neuron 483 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: 0.9000. Min Range: -0.9000

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1989154 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1783169 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1058877 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1759230 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7462. Min Act: -0.0000

Data Index: 300220 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1963125 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7392. Min Act: -0.0000

Data Index: 188792 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7415. Min Act: -0.0000

Data Index: 216009 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6513. Min Act: -0.0000

Data Index: 668172 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1353048 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1461877 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1216208 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5899. Min Act: -0.0000

Data Index: 510085 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5892. Min Act: -0.0000

Data Index: 748594 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1485940 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1570876 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1457714 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6031. Min Act: -0.0000

Data Index: 96538 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5143. Min Act: -0.0000

Data Index: 985705 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5851. Min Act: -0.0000

Data Index: 391270 (The Pile)

Max Activating Token Index: 786