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

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

Neuron 1084 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.7030. Min Act: -0.0000

Data Index: 396061 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.3487. Min Act: -0.0000

Data Index: 131214 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.0991. Min Act: -0.0000

Data Index: 1051102 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.9666. Min Act: -0.0000

Data Index: 73550 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.8812. Min Act: -0.0000

Data Index: 1124748 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.6681. Min Act: -0.0000

Data Index: 1057246 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.5843. Min Act: -0.0000

Data Index: 674752 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.3494. Min Act: -0.0000

Data Index: 65021 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.4271. Min Act: -0.0000

Data Index: 284261 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.4481. Min Act: -0.0000

Data Index: 695613 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.4040. Min Act: -0.0000

Data Index: 710565 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.5097. Min Act: -0.0000

Data Index: 640221 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.3674. Min Act: -0.0000

Data Index: 308586 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.2229. Min Act: -0.0000

Data Index: 1070854 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.3158. Min Act: -0.0000

Data Index: 1287951 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.2959. Min Act: -0.0000

Data Index: 47125 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.1773. Min Act: -0.0000

Data Index: 252274 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.2833. Min Act: -0.0000

Data Index: 505513 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.1579. Min Act: -0.0000

Data Index: 1203620 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.7030. Min Range: -3.7030

Max Act: 2.2665. Min Act: -0.0000

Data Index: 81892 (C4 (Web Text))

Max Activating Token Index: 449