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

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

Neuron 2193 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1092598 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.2256. Min Act: -0.0000

Data Index: 640146 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1324176 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1002323 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1966. Min Act: -0.0000

Data Index: 819809 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.2021. Min Act: -0.0000

Data Index: 792657 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1042655 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1993. Min Act: -0.0000

Data Index: 480126 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1849. Min Act: -0.0000

Data Index: 69389 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1227778 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.2013. Min Act: -0.0000

Data Index: 863579 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1258775 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1072321 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1830. Min Act: -0.0000

Data Index: 661131 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1895. Min Act: -0.0000

Data Index: 643639 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1798. Min Act: -0.0000

Data Index: 852089 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1084943 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1787. Min Act: -0.0000

Data Index: 614890 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1420134 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 0.5261. Min Range: -0.5261

Max Act: 0.1723. Min Act: -0.0000

Data Index: 376354 (C4 (Web Text))

Max Activating Token Index: 835