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

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

Neuron 1105 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5867. Min Act: -0.0001

Data Index: 1220513 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5879. Min Act: -0.0000

Data Index: 442498 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.6068. Min Act: -0.0001

Data Index: 542228 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.6237. Min Act: -0.0001

Data Index: 1038729 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4912. Min Act: -0.0001

Data Index: 519862 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5171. Min Act: -0.0001

Data Index: 406360 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1253054 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5912. Min Act: -0.0001

Data Index: 888413 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5270. Min Act: -0.0001

Data Index: 1276027 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5021. Min Act: -0.0001

Data Index: 780512 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4423. Min Act: -0.0000

Data Index: 270679 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4852. Min Act: -0.0001

Data Index: 106801 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5012. Min Act: -0.0001

Data Index: 323132 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4399. Min Act: -0.0000

Data Index: 680018 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4592. Min Act: -0.0001

Data Index: 1078090 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4744. Min Act: -0.0000

Data Index: 502813 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4678. Min Act: -0.0001

Data Index: 1494890 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4589. Min Act: -0.0001

Data Index: 1032781 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4704. Min Act: -0.0000

Data Index: 458497 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4898. Min Act: -0.0001

Data Index: 488897 (C4 (Web Text))

Max Activating Token Index: 722