Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2101 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0912. Min Act: -0.0001

Data Index: 574159 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1093625 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0889. Min Act: -0.0001

Data Index: 901488 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0851. Min Act: -0.0001

Data Index: 647591 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0884. Min Act: -0.0001

Data Index: 494259 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0825. Min Act: -0.0001

Data Index: 543632 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1135272 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0829. Min Act: -0.0001

Data Index: 95241 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1328984 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0776. Min Act: -0.0001

Data Index: 988915 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0827. Min Act: -0.0001

Data Index: 146079 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1284757 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0847. Min Act: -0.0001

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1235889 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0786. Min Act: -0.0001

Data Index: 990661 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1083312 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0807. Min Act: -0.0001

Data Index: 475749 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0777. Min Act: -0.0001

Data Index: 128018 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0792. Min Act: -0.0001

Data Index: 465854 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0719. Min Act: -0.0001

Data Index: 690059 (C4 (Web Text))

Max Activating Token Index: 551