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

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

Neuron 1123 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0003

Data Index: 725863 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0870. Min Act: -0.0003

Data Index: 1130790 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1412580 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1493359 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1420781 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1096398 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0726. Min Act: -0.0003

Data Index: 41598 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0699. Min Act: -0.0003

Data Index: 614646 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1360803 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1445038 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1622225 (Python Code)

Max Activating Token Index: 147

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0670. Min Act: -0.0003

Data Index: 967918 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1594831 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1515243 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1560155 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1611795 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1511824 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1563402 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1607683 (Python Code)

Max Activating Token Index: 208

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1549625 (Python Code)

Max Activating Token Index: 34