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

Dataset: The Pile

Neuron 3422 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1292787 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1727312 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.7653. Min Act: -0.0000

Data Index: 672705 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.8158. Min Act: -0.0000

Data Index: 707327 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1991590 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1483247 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6917. Min Act: -0.0000

Data Index: 492740 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6787. Min Act: -0.0000

Data Index: 998995 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1502150 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1579549 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6231. Min Act: -0.0000

Data Index: 683177 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1897837 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1533558 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1817206 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.7016. Min Act: -0.0000

Data Index: 87101 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1133038 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1299930 (The Pile)

Max Activating Token Index: 796

Text #17

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1524054 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1079279 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 0.9542. Min Range: -0.9542

Max Act: 0.6589. Min Act: -0.0000

Data Index: 423906 (The Pile)

Max Activating Token Index: 919