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

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

Neuron 4342 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: 0.0845. Min Range: -0.0845

Max Act: 0.0837. Min Act: -0.0002

Data Index: 164504 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0749. Min Act: -0.0002

Data Index: 801433 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0741. Min Act: -0.0002

Data Index: 897384 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1305668 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0806. Min Act: -0.0002

Data Index: 914590 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0672. Min Act: -0.0002

Data Index: 167093 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0746. Min Act: -0.0002

Data Index: 259304 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0735. Min Act: -0.0002

Data Index: 121378 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1198251 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0679. Min Act: -0.0002

Data Index: 200963 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0725. Min Act: -0.0002

Data Index: 75242 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1166118 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0710. Min Act: -0.0002

Data Index: 904320 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1297343 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0656. Min Act: -0.0002

Data Index: 848971 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0677. Min Act: -0.0002

Data Index: 660281 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1243920 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0707. Min Act: -0.0002

Data Index: 582698 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0663. Min Act: -0.0002

Data Index: 949410 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0656. Min Act: -0.0002

Data Index: 502153 (C4 (Web Text))

Max Activating Token Index: 18