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

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

Neuron 59 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: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0002

Data Index: 483591 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1351855 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1165965 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0794. Min Act: -0.0002

Data Index: 20974 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0811. Min Act: -0.0003

Data Index: 544707 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0792. Min Act: -0.0002

Data Index: 836337 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0762. Min Act: -0.0003

Data Index: 186951 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0781. Min Act: -0.0003

Data Index: 963071 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1270045 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1063952 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0761. Min Act: -0.0002

Data Index: 3821 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0753. Min Act: -0.0002

Data Index: 325860 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0745. Min Act: -0.0002

Data Index: 421212 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1039234 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0721. Min Act: -0.0002

Data Index: 321214 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0717. Min Act: -0.0002

Data Index: 360853 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0699. Min Act: -0.0002

Data Index: 318215 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0702. Min Act: -0.0003

Data Index: 901892 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0698. Min Act: -0.0002

Data Index: 741101 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0697. Min Act: -0.0002

Data Index: 251571 (C4 (Web Text))

Max Activating Token Index: 709