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

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

Neuron 598 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4871. Min Act: 0.0001

Data Index: 283144 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1280408 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4478. Min Act: -0.0000

Data Index: 163433 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3984. Min Act: -0.0000

Data Index: 500071 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3712. Min Act: 0.0000

Data Index: 69830 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3536. Min Act: -0.0000

Data Index: 252887 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3495. Min Act: -0.0000

Data Index: 199768 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3253. Min Act: -0.0000

Data Index: 192278 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3101. Min Act: 0.0001

Data Index: 811942 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3052. Min Act: -0.0000

Data Index: 154283 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3159. Min Act: -0.0000

Data Index: 815226 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3032. Min Act: -0.0000

Data Index: 858333 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.2969. Min Act: -0.0000

Data Index: 768134 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.2814. Min Act: 0.0002

Data Index: 752625 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.2985. Min Act: -0.0000

Data Index: 951418 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3084. Min Act: -0.0000

Data Index: 194492 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.2960. Min Act: 0.0002

Data Index: 548077 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.2933. Min Act: -0.0000

Data Index: 117807 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.2803. Min Act: 0.0002

Data Index: 938113 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.2750. Min Act: -0.0000

Data Index: 734641 (C4 (Web Text))

Max Activating Token Index: 869