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

Dataset: The Pile

Neuron 1019 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6904. Min Act: -0.0000

Data Index: 82562 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.2507. Min Act: -0.0000

Data Index: 808026 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1543966 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4583. Min Act: -0.0000

Data Index: 1126158 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1648120 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6178. Min Act: -0.0000

Data Index: 474927 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1510107 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4109. Min Act: -0.0000

Data Index: 1730763 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1509138 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6011. Min Act: -0.0000

Data Index: 1114971 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.5983. Min Act: -0.0000

Data Index: 552794 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.3427. Min Act: -0.0000

Data Index: 745792 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4771. Min Act: -0.0000

Data Index: 988689 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6968. Min Act: -0.0000

Data Index: 1678731 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1790212 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1790213 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4918. Min Act: -0.0000

Data Index: 41300 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.5059. Min Act: -0.0000

Data Index: 1044799 (The Pile)

Max Activating Token Index: 802

Text #18

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1740514 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.2724. Min Act: -0.0000

Data Index: 798404 (The Pile)

Max Activating Token Index: 950