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

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

Neuron 2018 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: 1.9684. Min Range: -1.9684

Max Act: 1.9684. Min Act: -0.0000

Data Index: 943148 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.7699. Min Act: -0.0000

Data Index: 445455 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.8981. Min Act: -0.0000

Data Index: 1183916 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.8072. Min Act: -0.0000

Data Index: 587579 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.4863. Min Act: -0.0000

Data Index: 448871 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1207379 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.6542. Min Act: -0.0000

Data Index: 330252 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5850. Min Act: -0.0000

Data Index: 481982 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5700. Min Act: -0.0000

Data Index: 839717 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5415. Min Act: -0.0000

Data Index: 505584 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1348502 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5121. Min Act: -0.0000

Data Index: 28710 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5054. Min Act: -0.0000

Data Index: 474250 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1247985 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.3774. Min Act: -0.0000

Data Index: 99571 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.4849. Min Act: -0.0000

Data Index: 73921 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.3259. Min Act: -0.0000

Data Index: 858436 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.4138. Min Act: -0.0000

Data Index: 660249 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.3271. Min Act: -0.0000

Data Index: 474463 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1079073 (C4 (Web Text))

Max Activating Token Index: 877