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

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

Neuron 586 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.8730. Min Act: -0.0000

Data Index: 37402 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1321397 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7671. Min Act: -0.0000

Data Index: 57154 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1238519 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7842. Min Act: -0.0000

Data Index: 721450 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6685. Min Act: -0.0000

Data Index: 751157 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1253980 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6969. Min Act: 0.0000

Data Index: 1033848 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1087847 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6639. Min Act: -0.0000

Data Index: 265038 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6172. Min Act: -0.0000

Data Index: 296897 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6202. Min Act: -0.0000

Data Index: 877827 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5847. Min Act: -0.0000

Data Index: 532050 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1266479 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5479. Min Act: -0.0000

Data Index: 223295 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5664. Min Act: -0.0000

Data Index: 948297 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5100. Min Act: -0.0000

Data Index: 661126 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5907. Min Act: 0.0001

Data Index: 1178228 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1039713 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1193555 (C4 (Web Text))

Max Activating Token Index: 771