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

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

Neuron 3450 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: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0002

Data Index: 38243 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1075. Min Act: -0.0001

Data Index: 318998 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1277929 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1050. Min Act: -0.0002

Data Index: 734417 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0897. Min Act: -0.0002

Data Index: 12084 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1026. Min Act: -0.0001

Data Index: 420047 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1048. Min Act: -0.0001

Data Index: 849165 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1357532 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0952. Min Act: -0.0001

Data Index: 125945 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1183051 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0879. Min Act: -0.0001

Data Index: 204329 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1309177 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0873. Min Act: -0.0001

Data Index: 134148 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0841. Min Act: -0.0001

Data Index: 589912 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0885. Min Act: -0.0002

Data Index: 426400 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0799. Min Act: -0.0001

Data Index: 709185 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0906. Min Act: -0.0001

Data Index: 495128 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1210291 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1200690 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1270732 (C4 (Web Text))

Max Activating Token Index: 45