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

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

Neuron 1822 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.8735. Min Act: -0.0000

Data Index: 18385 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6208. Min Act: -0.0000

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.5777. Min Act: 0.0000

Data Index: 496701 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.4801. Min Act: -0.0000

Data Index: 319315 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2487. Min Act: -0.0000

Data Index: 230834 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2655. Min Act: -0.0000

Data Index: 325847 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2917. Min Act: -0.0000

Data Index: 593870 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2879. Min Act: -0.0000

Data Index: 848222 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1102635 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.1800. Min Act: -0.0000

Data Index: 722624 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1009484 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2454. Min Act: -0.0000

Data Index: 838630 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2088. Min Act: 0.0001

Data Index: 295691 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.1630. Min Act: -0.0000

Data Index: 153941 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1244231 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1296790 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.1889. Min Act: -0.0000

Data Index: 6761 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.1855. Min Act: -0.0000

Data Index: 276112 (C4 (Web Text))

Max Activating Token Index: 177