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

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

Neuron 482 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3755. Min Act: -0.0000

Data Index: 338434 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3551. Min Act: -0.0000

Data Index: 317180 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1303379 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1316456 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3140. Min Act: -0.0000

Data Index: 519947 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3020. Min Act: -0.0000

Data Index: 362602 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2855. Min Act: -0.0000

Data Index: 505239 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2937. Min Act: -0.0000

Data Index: 469921 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2892. Min Act: -0.0000

Data Index: 905878 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1089255 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1390005 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1606550 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2732. Min Act: -0.0000

Data Index: 475975 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2796. Min Act: -0.0000

Data Index: 748212 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2850. Min Act: -0.0000

Data Index: 63397 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1119919 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1146041 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2451. Min Act: -0.0000

Data Index: 379694 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2673. Min Act: -0.0000

Data Index: 478139 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1233653 (C4 (Web Text))

Max Activating Token Index: 461