Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4840 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0002

Data Index: 307514 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1145. Min Act: -0.0002

Data Index: 21690 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1087. Min Act: -0.0003

Data Index: 1162011 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1087. Min Act: -0.0002

Data Index: 888721 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1050. Min Act: -0.0002

Data Index: 8187 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1097595 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1037. Min Act: -0.0002

Data Index: 492845 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1023. Min Act: -0.0003

Data Index: 1164716 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1000. Min Act: -0.0002

Data Index: 779668 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1355129 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1005010 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0985. Min Act: -0.0002

Data Index: 352421 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0955. Min Act: -0.0002

Data Index: 103825 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0957. Min Act: -0.0002

Data Index: 503716 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0984. Min Act: -0.0002

Data Index: 645173 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1338228 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0950. Min Act: -0.0002

Data Index: 424537 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0972. Min Act: -0.0002

Data Index: 127532 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0963. Min Act: -0.0002

Data Index: 994585 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0958. Min Act: -0.0002

Data Index: 779738 (C4 (Web Text))

Max Activating Token Index: 24