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

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

Neuron 3670 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0002

Data Index: 606628 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0905. Min Act: -0.0002

Data Index: 697541 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0748. Min Act: -0.0002

Data Index: 984234 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0742. Min Act: -0.0002

Data Index: 884880 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1071931 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0687. Min Act: -0.0002

Data Index: 890424 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0684. Min Act: -0.0002

Data Index: 586327 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1084917 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0672. Min Act: -0.0002

Data Index: 446176 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0669. Min Act: -0.0002

Data Index: 126241 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1049605 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0646. Min Act: -0.0002

Data Index: 76412 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0673. Min Act: -0.0002

Data Index: 655341 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1100118 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1318571 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1019340 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0620. Min Act: -0.0002

Data Index: 991114 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1126990 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0591. Min Act: -0.0002

Data Index: 246591 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0607. Min Act: -0.0002

Data Index: 576402 (C4 (Web Text))

Max Activating Token Index: 278