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

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

Neuron 4677 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1130709 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0912. Min Act: -0.0001

Data Index: 10196 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1271733 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0900. Min Act: -0.0001

Data Index: 698978 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0798. Min Act: -0.0001

Data Index: 14979 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0824. Min Act: -0.0001

Data Index: 343324 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0885. Min Act: -0.0001

Data Index: 540336 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1057924 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0790. Min Act: -0.0001

Data Index: 223720 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0751. Min Act: -0.0001

Data Index: 867526 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0759. Min Act: -0.0001

Data Index: 319464 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0820. Min Act: -0.0001

Data Index: 617132 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0777. Min Act: -0.0001

Data Index: 499987 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0692. Min Act: -0.0001

Data Index: 722260 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0684. Min Act: -0.0001

Data Index: 958508 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0717. Min Act: -0.0001

Data Index: 240825 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1175104 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0737. Min Act: -0.0001

Data Index: 749973 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0721. Min Act: -0.0001

Data Index: 425879 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0721. Min Act: -0.0001

Data Index: 70546 (C4 (Web Text))

Max Activating Token Index: 993