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

Dataset: The Pile

Neuron 746 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: 0.5836. Min Range: -0.5836

Max Act: 0.5836. Min Act: -0.0000

Data Index: 189595 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.5097. Min Act: -0.0000

Data Index: 661083 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1087728 (The Pile)

Max Activating Token Index: 916

Text #3

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1372260 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1374635 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4145. Min Act: -0.0000

Data Index: 695689 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.4096. Min Act: -0.0000

Data Index: 215390 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1468016 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1342934 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1883348 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3220. Min Act: -0.0000

Data Index: 541942 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3862. Min Act: -0.0000

Data Index: 53935 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3450. Min Act: -0.0000

Data Index: 516668 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1080614 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1897480 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3057. Min Act: -0.0000

Data Index: 988121 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.2916. Min Act: -0.0000

Data Index: 768468 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3184. Min Act: -0.0000

Data Index: 53864 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3292. Min Act: -0.0000

Data Index: 574247 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.5836. Min Range: -0.5836

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1683330 (The Pile)

Max Activating Token Index: 713