Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 737 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1131. Min Act: -0.0003

Data Index: 623029 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1098. Min Act: -0.0003

Data Index: 1169012 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1010. Min Act: -0.0004

Data Index: 780028 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1044. Min Act: -0.0004

Data Index: 1345772 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1020347 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1027. Min Act: -0.0003

Data Index: 60359 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1052. Min Act: -0.0003

Data Index: 838435 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1005. Min Act: -0.0003

Data Index: 550426 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0977. Min Act: -0.0004

Data Index: 699160 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0966. Min Act: -0.0003

Data Index: 1342128 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0953. Min Act: -0.0003

Data Index: 67758 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0967. Min Act: -0.0003

Data Index: 108855 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0948. Min Act: -0.0004

Data Index: 980366 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0930. Min Act: -0.0003

Data Index: 665652 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0946. Min Act: -0.0003

Data Index: 789405 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0928. Min Act: -0.0004

Data Index: 85313 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1241468 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0880. Min Act: -0.0003

Data Index: 658237 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0916. Min Act: -0.0003

Data Index: 121004 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0968. Min Act: -0.0003

Data Index: 395549 (C4 (Web Text))

Max Activating Token Index: 677