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

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

Neuron 785 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.7085. Min Act: -0.0001

Data Index: 12070 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.5690. Min Act: -0.0001

Data Index: 1035273 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.4946. Min Act: -0.0001

Data Index: 758386 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.4574. Min Act: -0.0001

Data Index: 1238664 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.4016. Min Act: -0.0001

Data Index: 434592 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.2602. Min Act: -0.0001

Data Index: 1041606 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.2792. Min Act: -0.0001

Data Index: 1314390 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.2311. Min Act: -0.0001

Data Index: 572226 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.0893. Min Act: -0.0001

Data Index: 863100 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.2272. Min Act: -0.0001

Data Index: 684484 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.1070. Min Act: -0.0001

Data Index: 896779 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.7085. Min Range: -1.7085

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1230869 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.0128. Min Act: -0.0001

Data Index: 617531 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.1066. Min Act: -0.0001

Data Index: 109669 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.0609. Min Act: -0.0001

Data Index: 1094753 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.7085. Min Range: -1.7085

Max Act: 0.9652. Min Act: -0.0001

Data Index: 986039 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.0613. Min Act: -0.0001

Data Index: 311519 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 1.7085. Min Range: -1.7085

Max Act: 0.9958. Min Act: -0.0001

Data Index: 622041 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.7085. Min Range: -1.7085

Max Act: 1.0284. Min Act: -0.0001

Data Index: 516661 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.7085. Min Range: -1.7085

Max Act: 0.9891. Min Act: -0.0001

Data Index: 505554 (C4 (Web Text))

Max Activating Token Index: 703