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

Dataset: The Pile

Neuron 2815 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: 0.9829. Min Range: -0.9829

Max Act: 0.9829. Min Act: -0.0000

Data Index: 724494 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9815. Min Act: -0.0000

Data Index: 176516 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1809152 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8570. Min Act: -0.0000

Data Index: 51760 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8849. Min Act: -0.0000

Data Index: 421184 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8243. Min Act: -0.0000

Data Index: 326693 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8083. Min Act: -0.0000

Data Index: 657419 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1723133 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7903. Min Act: -0.0000

Data Index: 147030 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1493055 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1107511 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1631369 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1621867 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1124178 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1727512 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7919. Min Act: -0.0000

Data Index: 554009 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7495. Min Act: -0.0000

Data Index: 433610 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7408. Min Act: -0.0000

Data Index: 583945 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1149614 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7415. Min Act: -0.0000

Data Index: 864901 (The Pile)

Max Activating Token Index: 820