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

Dataset: The Pile

Neuron 1204 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.4753. Min Act: -0.0000

Data Index: 1900067 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.4345. Min Act: -0.0000

Data Index: 688423 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8768. Min Act: -0.0000

Data Index: 1385105 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.4317. Min Act: -0.0000

Data Index: 1319947 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.5767. Min Act: -0.0000

Data Index: 1447949 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7117. Min Act: -0.0000

Data Index: 344780 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.0629. Min Act: -0.0000

Data Index: 1562414 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.2947. Min Act: -0.0000

Data Index: 1587331 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.0354. Min Act: -0.0000

Data Index: 1208629 (The Pile)

Max Activating Token Index: 118

Text #9

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.2933. Min Act: -0.0000

Data Index: 1167480 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.0413. Min Act: -0.0000

Data Index: 760044 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.0885. Min Act: -0.0000

Data Index: 1816628 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 3.8768. Min Range: -3.8768

Max Act: 2.9543. Min Act: -0.0000

Data Index: 1668417 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.2121. Min Act: -0.0000

Data Index: 1601597 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 3.8768. Min Range: -3.8768

Max Act: 2.8313. Min Act: -0.0000

Data Index: 1770029 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.2501. Min Act: -0.0000

Data Index: 962862 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.1318. Min Act: -0.0000

Data Index: 1990289 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.0786. Min Act: -0.0000

Data Index: 1494115 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 3.8768. Min Range: -3.8768

Max Act: 2.6139. Min Act: -0.0000

Data Index: 1032433 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 3.8768. Min Range: -3.8768

Max Act: 2.8353. Min Act: -0.0000

Data Index: 303173 (The Pile)

Max Activating Token Index: 137