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

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

Neuron 4574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1195. Min Range: -1.1195

Max Act: 1.1195. Min Act: -0.0000

Data Index: 741546 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.9340. Min Act: -0.0000

Data Index: 787344 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 1.1195. Min Range: -1.1195

Max Act: 1.0187. Min Act: -0.0000

Data Index: 149972 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.9654. Min Act: -0.0000

Data Index: 502649 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.9246. Min Act: -0.0000

Data Index: 4159 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.9501. Min Act: -0.0000

Data Index: 892647 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8920. Min Act: -0.0000

Data Index: 701298 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 1.1195. Min Range: -1.1195

Max Act: 1.0030. Min Act: -0.0000

Data Index: 495737 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.9445. Min Act: -0.0000

Data Index: 415010 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8248. Min Act: -0.0000

Data Index: 589843 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1150775 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8525. Min Act: -0.0000

Data Index: 795366 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8944. Min Act: -0.0000

Data Index: 913655 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1151728 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8882. Min Act: -0.0000

Data Index: 699307 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8655. Min Act: -0.0000

Data Index: 66048 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1121262 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8488. Min Act: -0.0000

Data Index: 989499 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.9016. Min Act: -0.0000

Data Index: 692478 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.1195. Min Range: -1.1195

Max Act: 0.8978. Min Act: -0.0000

Data Index: 39515 (C4 (Web Text))

Max Activating Token Index: 755