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

Dataset: The Pile

Neuron 3048 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: 11.0185. Min Range: -11.0185

Max Act: 11.0185. Min Act: -0.0000

Data Index: 1036527 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.9855. Min Act: -0.0000

Data Index: 1293357 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.6900. Min Act: -0.0000

Data Index: 1470593 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.5129. Min Act: -0.0000

Data Index: 911032 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.7387. Min Act: -0.0000

Data Index: 21596 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.5690. Min Act: -0.0000

Data Index: 30797 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.3276. Min Act: -0.0000

Data Index: 761501 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.2759. Min Act: -0.0000

Data Index: 1426842 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.2632. Min Act: -0.0000

Data Index: 223145 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.4024. Min Act: -0.0000

Data Index: 927832 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 11.0185. Min Range: -11.0185

Max Act: 8.7673. Min Act: -0.0000

Data Index: 541676 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.3958. Min Act: -0.0000

Data Index: 1478269 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.2801. Min Act: -0.0000

Data Index: 727619 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.0633. Min Act: -0.0000

Data Index: 1368693 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.1878. Min Act: -0.0000

Data Index: 1736705 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.4102. Min Act: -0.0000

Data Index: 1285496 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.0861. Min Act: -0.0000

Data Index: 999547 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.5509. Min Act: -0.0000

Data Index: 469378 (The Pile)

Max Activating Token Index: 884

Text #18

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.2209. Min Act: -0.0000

Data Index: 645923 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 11.0185. Min Range: -11.0185

Max Act: 9.0576. Min Act: -0.0000

Data Index: 1644776 (The Pile)

Max Activating Token Index: 55