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

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

Neuron 1307 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0104. Min Act: -0.0002

Data Index: 3414 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0102. Min Act: -0.0002

Data Index: 217356 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1272797 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1211377 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0099. Min Act: -0.0002

Data Index: 137609 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1349302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0097. Min Act: -0.0002

Data Index: 335653 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0097. Min Act: -0.0002

Data Index: 848076 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0002

Data Index: 979095 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0002

Data Index: 392290 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0002

Data Index: 398471 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1150570 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0002

Data Index: 104286 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1317420 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0002

Data Index: 723537 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0092. Min Act: -0.0002

Data Index: 193130 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1434799 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1611212 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0002

Data Index: 549854 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0002

Data Index: 16965 (C4 (Web Text))

Max Activating Token Index: 1