Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 980 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1414. Min Act: -0.0002

Data Index: 224304 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1179. Min Act: -0.0002

Data Index: 247048 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1168416 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1193. Min Act: -0.0002

Data Index: 1311879 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1131913 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1024. Min Act: -0.0002

Data Index: 260962 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1099766 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1160033 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1053. Min Act: -0.0002

Data Index: 509203 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0989. Min Act: -0.0002

Data Index: 272462 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0992. Min Act: -0.0002

Data Index: 30841 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0980. Min Act: -0.0002

Data Index: 908373 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0976. Min Act: -0.0002

Data Index: 886644 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0982. Min Act: -0.0002

Data Index: 939736 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1211153 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1023. Min Act: -0.0002

Data Index: 719130 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0972. Min Act: -0.0002

Data Index: 52138 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1232319 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0965. Min Act: -0.0002

Data Index: 569001 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0986. Min Act: -0.0002

Data Index: 692175 (C4 (Web Text))

Max Activating Token Index: 13