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

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

Neuron 3874 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6642. Min Act: -0.0002

Data Index: 938132 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6689. Min Act: -0.0002

Data Index: 825222 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6717. Min Act: -0.0002

Data Index: 998679 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5978. Min Act: -0.0002

Data Index: 433748 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6205. Min Act: -0.0002

Data Index: 515036 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6775. Min Act: -0.0002

Data Index: 242161 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5933. Min Act: -0.0002

Data Index: 749673 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5676. Min Act: -0.0002

Data Index: 439923 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5705. Min Act: -0.0002

Data Index: 815330 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5842. Min Act: -0.0002

Data Index: 1111650 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6501. Min Act: -0.0002

Data Index: 1012913 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6164. Min Act: -0.0002

Data Index: 329800 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6110. Min Act: -0.0002

Data Index: 1243927 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5447. Min Act: -0.0002

Data Index: 513089 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6433. Min Act: -0.0002

Data Index: 1013420 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5977. Min Act: -0.0002

Data Index: 1294829 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6071. Min Act: -0.0002

Data Index: 878939 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5590. Min Act: -0.0002

Data Index: 856521 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.7036. Min Act: -0.0002

Data Index: 1331624 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6117. Min Act: -0.0002

Data Index: 230136 (C4 (Web Text))

Max Activating Token Index: 335