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

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

Neuron 2725 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4960. Min Range: -2.4960

Max Act: 2.4960. Min Act: -0.0000

Data Index: 837954 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.4960. Min Range: -2.4960

Max Act: 2.3115. Min Act: -0.0000

Data Index: 1293816 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.8903. Min Act: -0.0000

Data Index: 1234317 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.7830. Min Act: -0.0000

Data Index: 305202 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.6722. Min Act: -0.0000

Data Index: 191147 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.6017. Min Act: -0.0000

Data Index: 42968 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.5680. Min Act: -0.0000

Data Index: 5881 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.5996. Min Act: -0.0000

Data Index: 906534 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.4624. Min Act: -0.0000

Data Index: 775294 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.3729. Min Act: -0.0000

Data Index: 517121 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.5728. Min Act: -0.0000

Data Index: 887441 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.3334. Min Act: -0.0000

Data Index: 227763 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.3344. Min Act: -0.0000

Data Index: 522904 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.4064. Min Act: -0.0000

Data Index: 12801 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1042539 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.3104. Min Act: -0.0000

Data Index: 720611 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.2963. Min Act: -0.0000

Data Index: 385477 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.2793. Min Act: -0.0000

Data Index: 2522 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.2836. Min Act: -0.0000

Data Index: 968110 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 2.4960. Min Range: -2.4960

Max Act: 1.1832. Min Act: -0.0000

Data Index: 683012 (C4 (Web Text))

Max Activating Token Index: 848