Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3927 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0003

Data Index: 797428 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 419447 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1194208 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1554502 (Python Code)

Max Activating Token Index: 1010

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0003

Data Index: 162444 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0003

Data Index: 170519 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0043. Min Act: -0.0003

Data Index: 189426 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1201033 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0003

Data Index: 929212 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1213315 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0003

Data Index: 135473 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1487123 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0003

Data Index: 610878 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0003

Data Index: 918462 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0043. Min Act: -0.0003

Data Index: 682242 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1597162 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1248537 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0003

Data Index: 341220 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0003

Data Index: 89298 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0003

Data Index: 31631 (C4 (Web Text))

Max Activating Token Index: 30