Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2187 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1329353 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0003

Data Index: 642472 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0050. Min Act: -0.0003

Data Index: 859951 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0049. Min Act: -0.0004

Data Index: 934536 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0049. Min Act: -0.0003

Data Index: 86130 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0003

Data Index: 568760 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1241836 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0004

Data Index: 1339123 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1555988 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0004

Data Index: 743707 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1328520 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0004

Data Index: 571120 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1507668 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0003

Data Index: 877077 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0047. Min Act: -0.0003

Data Index: 682269 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1080178 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0047. Min Act: -0.0003

Data Index: 615363 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0047. Min Act: -0.0004

Data Index: 286762 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0047. Min Act: -0.0003

Data Index: 748884 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0047. Min Act: -0.0003

Data Index: 750626 (C4 (Web Text))

Max Activating Token Index: 43