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

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

Neuron 3166 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9549. Min Act: -0.0002

Data Index: 319057 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8512. Min Act: -0.0002

Data Index: 600763 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.6128. Min Act: -0.0001

Data Index: 725082 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.6139. Min Act: -0.0002

Data Index: 467286 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.5768. Min Act: -0.0001

Data Index: 1349032 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.6277. Min Act: -0.0001

Data Index: 1063195 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.5804. Min Act: -0.0002

Data Index: 944737 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.6232. Min Act: -0.0001

Data Index: 1103120 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.4522. Min Act: -0.0002

Data Index: 927426 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.4870. Min Act: -0.0002

Data Index: 515495 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.3542. Min Act: -0.0001

Data Index: 237858 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.4634. Min Act: -0.0001

Data Index: 1194456 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.5374. Min Act: -0.0002

Data Index: 1083118 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.3117. Min Act: -0.0002

Data Index: 1246221 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.5400. Min Act: -0.0001

Data Index: 743768 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.6161. Min Act: -0.0002

Data Index: 822913 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.3196. Min Act: -0.0001

Data Index: 310417 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.3960. Min Act: -0.0001

Data Index: 1300171 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.3457. Min Act: -0.0002

Data Index: 558558 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.3452. Min Act: -0.0001

Data Index: 1181767 (C4 (Web Text))

Max Activating Token Index: 949