Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1133 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0047. Min Act: -0.0006

Data Index: 765919 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0006

Data Index: 761572 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0047. Min Act: -0.0006

Data Index: 634836 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1044152 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0006

Data Index: 825222 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 670866 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 248582 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 470091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0006

Data Index: 791874 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0006

Data Index: 908379 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0006

Data Index: 277329 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0006

Data Index: 742427 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0040. Min Act: -0.0006

Data Index: 483914 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0006

Data Index: 935660 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0006

Data Index: 663652 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0040. Min Act: -0.0005

Data Index: 985788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0006

Data Index: 933243 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0006

Data Index: 390428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0006

Data Index: 925304 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0006

Data Index: 212585 (C4 (Web Text))

Max Activating Token Index: 1020