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

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

Neuron 3697 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0119. Min Act: -0.0002

Data Index: 92228 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0104. Min Act: -0.0002

Data Index: 642723 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1297757 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0103. Min Act: -0.0002

Data Index: 948805 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0107. Min Act: -0.0003

Data Index: 839360 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1566133 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0095. Min Act: -0.0003

Data Index: 717718 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1451409 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0091. Min Act: -0.0002

Data Index: 467728 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0097. Min Act: -0.0003

Data Index: 926622 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1587855 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1267072 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1188978 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1600443 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1368963 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0092. Min Act: -0.0003

Data Index: 257531 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0092. Min Act: -0.0002

Data Index: 251817 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0091. Min Act: -0.0002

Data Index: 661491 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0091. Min Act: -0.0003

Data Index: 574456 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0094. Min Act: -0.0003

Data Index: 597781 (C4 (Web Text))

Max Activating Token Index: 894