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

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

Neuron 4633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.2937. Min Act: -0.0000

Data Index: 88679 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1334292 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0457. Min Act: -0.0000

Data Index: 527460 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1184169 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0139. Min Act: -0.0000

Data Index: 72765 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9720. Min Act: -0.0000

Data Index: 217812 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8364. Min Act: -0.0000

Data Index: 478210 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8636. Min Act: -0.0000

Data Index: 908927 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8500. Min Act: -0.0000

Data Index: 5038 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.7945. Min Act: -0.0000

Data Index: 128836 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8482. Min Act: -0.0000

Data Index: 148188 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8693. Min Act: -0.0000

Data Index: 22611 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8366. Min Act: -0.0000

Data Index: 761871 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1352785 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8058. Min Act: -0.0000

Data Index: 852330 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8009. Min Act: -0.0000

Data Index: 807017 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1083823 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8101. Min Act: -0.0000

Data Index: 475103 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.7807. Min Act: -0.0000

Data Index: 995200 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.7722. Min Act: -0.0000

Data Index: 829327 (C4 (Web Text))

Max Activating Token Index: 23