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

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

Neuron 4191 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: 0.0740. Min Range: -0.0740

Max Act: 0.0735. Min Act: -0.0002

Data Index: 506366 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0002

Data Index: 885971 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1352354 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1046072 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1192178 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0717. Min Act: -0.0002

Data Index: 662982 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0706. Min Act: -0.0002

Data Index: 589140 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0700. Min Act: -0.0002

Data Index: 357098 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0696. Min Act: -0.0002

Data Index: 687695 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0688. Min Act: -0.0002

Data Index: 629748 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1332059 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0681. Min Act: -0.0002

Data Index: 889119 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0689. Min Act: -0.0002

Data Index: 188907 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0687. Min Act: -0.0003

Data Index: 315600 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1126291 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1046079 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0661. Min Act: -0.0002

Data Index: 965035 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0672. Min Act: -0.0002

Data Index: 64220 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0659. Min Act: -0.0002

Data Index: 916485 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1260145 (C4 (Web Text))

Max Activating Token Index: 22