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

Dataset: The Pile

Neuron 943 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.8364. Min Act: -0.0000

Data Index: 107859 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7640. Min Act: -0.0000

Data Index: 664410 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7660. Min Act: -0.0000

Data Index: 237936 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1635176 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1112954 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1691827 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7767. Min Act: -0.0000

Data Index: 830509 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7488. Min Act: -0.0000

Data Index: 129031 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1428207 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7414. Min Act: -0.0000

Data Index: 166368 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1702305 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7161. Min Act: -0.0000

Data Index: 603754 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7341. Min Act: -0.0000

Data Index: 581826 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7120. Min Act: -0.0000

Data Index: 338655 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7091. Min Act: -0.0000

Data Index: 920 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1419378 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7684. Min Act: -0.0000

Data Index: 678121 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6859. Min Act: -0.0000

Data Index: 705593 (The Pile)

Max Activating Token Index: 167

Text #18

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1997598 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6691. Min Act: -0.0000

Data Index: 948636 (The Pile)

Max Activating Token Index: 108