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

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

Neuron 2154 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: 3.0426. Min Range: -3.0426

Max Act: 3.0426. Min Act: -0.0000

Data Index: 1249988 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 3.0426. Min Range: -3.0426

Max Act: 3.0163. Min Act: -0.0000

Data Index: 1256093 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.9985. Min Act: -0.0000

Data Index: 933136 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.8517. Min Act: -0.0000

Data Index: 1096777 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.9725. Min Act: -0.0000

Data Index: 1101426 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.8862. Min Act: -0.0000

Data Index: 317491 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.8571. Min Act: -0.0000

Data Index: 1127822 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.9805. Min Act: -0.0000

Data Index: 1146301 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.8212. Min Act: -0.0000

Data Index: 548142 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.6489. Min Act: -0.0000

Data Index: 837889 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.6208. Min Act: -0.0000

Data Index: 102992 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.5713. Min Act: -0.0000

Data Index: 1190736 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.7031. Min Act: -0.0000

Data Index: 5145 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.5149. Min Act: -0.0000

Data Index: 1264820 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.5595. Min Act: -0.0000

Data Index: 458847 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.6490. Min Act: -0.0000

Data Index: 795684 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.5226. Min Act: -0.0000

Data Index: 1208874 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.4752. Min Act: -0.0000

Data Index: 269609 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.3283. Min Act: -0.0000

Data Index: 1335529 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 3.0426. Min Range: -3.0426

Max Act: 2.5681. Min Act: -0.0000

Data Index: 459678 (C4 (Web Text))

Max Activating Token Index: 165