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

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

Neuron 251 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.1175. Min Act: -0.0002

Data Index: 643531 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.1009. Min Act: -0.0002

Data Index: 324473 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.1010. Min Act: -0.0002

Data Index: 669864 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1470174 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0978. Min Act: -0.0002

Data Index: 172099 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0987. Min Act: -0.0002

Data Index: 985353 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1567869 (Python Code)

Max Activating Token Index: 794

Text #7

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1023901 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1311665 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1160710 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1330682 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0927. Min Act: -0.0002

Data Index: 35434 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1171941 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1617753 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1056690 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1503018 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1625559 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0875. Min Act: -0.0002

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0893. Min Act: -0.0002

Data Index: 287735 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.1175. Min Range: -0.1175

Max Act: 0.0868. Min Act: -0.0002

Data Index: 554823 (C4 (Web Text))

Max Activating Token Index: 543