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

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

Neuron 2767 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: 0.3697. Min Range: -0.3697

Max Act: 0.3697. Min Act: -0.0000

Data Index: 170644 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1290108 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3274. Min Act: -0.0000

Data Index: 952005 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3285. Min Act: -0.0000

Data Index: 393510 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3097. Min Act: -0.0000

Data Index: 730899 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3263. Min Act: -0.0000

Data Index: 952998 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1067414 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2937. Min Act: -0.0000

Data Index: 798914 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3208. Min Act: -0.0000

Data Index: 448024 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2908. Min Act: -0.0000

Data Index: 353451 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2937. Min Act: -0.0000

Data Index: 965809 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3112. Min Act: -0.0000

Data Index: 427317 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2897. Min Act: -0.0000

Data Index: 191521 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1221514 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2819. Min Act: -0.0000

Data Index: 301013 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3016. Min Act: -0.0000

Data Index: 664867 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1306931 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1029251 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1337698 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1199867 (C4 (Web Text))

Max Activating Token Index: 885