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

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

Neuron 3658 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1307292 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0002

Data Index: 504761 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0002

Data Index: 929661 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0002

Data Index: 849278 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0002

Data Index: 80823 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0002

Data Index: 75226 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0002

Data Index: 16052 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1030130 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1180115 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0002

Data Index: 999131 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0002

Data Index: 57096 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0002

Data Index: 738994 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1261917 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0002

Data Index: 652291 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1081179 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1286220 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 452922 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1044561 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1109291 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0002

Data Index: 802999 (C4 (Web Text))

Max Activating Token Index: 642