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

Dataset: The Pile

Neuron 3038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1400093 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7328. Min Act: -0.0000

Data Index: 460029 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1769185 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1897124 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1170493 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7194. Min Act: -0.0000

Data Index: 602095 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6364. Min Act: -0.0000

Data Index: 909807 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7228. Min Act: -0.0000

Data Index: 964094 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1997542 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6531. Min Act: -0.0000

Data Index: 333426 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1766623 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6341. Min Act: -0.0000

Data Index: 751727 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1591987 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6737. Min Act: -0.0000

Data Index: 396983 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1070162 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1628848 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6546. Min Act: -0.0000

Data Index: 864829 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1753313 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1599952 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6416. Min Act: -0.0000

Data Index: 526244 (The Pile)

Max Activating Token Index: 384