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

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

Neuron 1165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1610535 (Python Code)

Max Activating Token Index: 808

Text #1

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1630471 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1410987 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1464034 (Python Code)

Max Activating Token Index: 710

Text #4

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1469055 (Python Code)

Max Activating Token Index: 782

Text #5

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1545546 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1528070 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1248589 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1522999 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1656144 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1369867 (Python Code)

Max Activating Token Index: 815

Text #11

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1375025 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1530218 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1366645 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0856. Min Act: -0.0002

Data Index: 312101 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1472615 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1654183 (Python Code)

Max Activating Token Index: 554

Text #17

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0801. Min Act: -0.0002

Data Index: 79473 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0855. Min Act: -0.0002

Data Index: 806159 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1485260 (Python Code)

Max Activating Token Index: 220