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

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

Neuron 3740 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1352341 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0003

Data Index: 695675 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0039. Min Act: -0.0003

Data Index: 554853 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0042. Min Act: -0.0003

Data Index: 333351 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1056565 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0038. Min Act: -0.0003

Data Index: 308750 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0042. Min Act: -0.0003

Data Index: 131761 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0034. Min Act: -0.0003

Data Index: 542108 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1074027 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0033. Min Act: -0.0003

Data Index: 866895 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0033. Min Act: -0.0002

Data Index: 635095 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0031. Min Act: -0.0003

Data Index: 26160 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0029. Min Act: -0.0003

Data Index: 1131535 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0027. Min Act: -0.0003

Data Index: 1122226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0031. Min Act: -0.0003

Data Index: 298949 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0028. Min Act: -0.0003

Data Index: 402218 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0029. Min Act: -0.0003

Data Index: 759002 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0027. Min Act: -0.0003

Data Index: 743237 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1015941 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0027. Min Act: -0.0003

Data Index: 661105 (C4 (Web Text))

Max Activating Token Index: 1023