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

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

Neuron 4195 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.4183. Min Act: -0.0000

Data Index: 271515 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1143. Min Act: -0.0000

Data Index: 604480 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9575. Min Act: -0.0000

Data Index: 749231 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1052030 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9202. Min Act: -0.0000

Data Index: 311872 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8735. Min Act: -0.0000

Data Index: 585266 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1048213 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9045. Min Act: -0.0000

Data Index: 409793 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8965. Min Act: -0.0000

Data Index: 145533 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9828. Min Act: -0.0000

Data Index: 321152 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8937. Min Act: -0.0000

Data Index: 440183 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8384. Min Act: -0.0001

Data Index: 916570 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8558. Min Act: -0.0000

Data Index: 903285 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8308. Min Act: 0.0000

Data Index: 1154983 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8515. Min Act: -0.0000

Data Index: 448132 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8285. Min Act: -0.0000

Data Index: 508978 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1116998 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1213972 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8412. Min Act: -0.0000

Data Index: 54722 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.7597. Min Act: -0.0000

Data Index: 118035 (C4 (Web Text))

Max Activating Token Index: 1013