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

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

Neuron 3672 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4696. Min Act: -0.0000

Data Index: 889463 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1253914 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4175. Min Act: -0.0000

Data Index: 807274 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4283. Min Act: 0.0000

Data Index: 512008 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4253. Min Act: 0.0000

Data Index: 948371 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4174. Min Act: 0.0000

Data Index: 1099619 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1020948 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3858. Min Act: 0.0001

Data Index: 874758 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4077. Min Act: 0.0000

Data Index: 1058251 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.4006. Min Act: -0.0000

Data Index: 743069 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1226364 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3945. Min Act: 0.0001

Data Index: 1615 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3935. Min Act: 0.0001

Data Index: 1185965 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3849. Min Act: -0.0000

Data Index: 593862 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3827. Min Act: 0.0000

Data Index: 375419 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1315533 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3992. Min Act: -0.0000

Data Index: 290574 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1067609 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1264744 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.4696. Min Range: -0.4696

Max Act: 0.3663. Min Act: -0.0000

Data Index: 89890 (C4 (Web Text))

Max Activating Token Index: 929