Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1518 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1261207 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0881. Min Act: -0.0002

Data Index: 156379 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0868. Min Act: -0.0002

Data Index: 42987 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0825. Min Act: -0.0001

Data Index: 314675 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0833. Min Act: -0.0001

Data Index: 562844 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0888. Min Act: -0.0002

Data Index: 191744 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0880. Min Act: -0.0002

Data Index: 540043 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1218346 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0831. Min Act: -0.0002

Data Index: 39400 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1494571 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0785. Min Act: -0.0002

Data Index: 766278 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1421960 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1434931 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1575157 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0842. Min Act: -0.0001

Data Index: 487759 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1570917 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1654441 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1377504 (Python Code)

Max Activating Token Index: 337

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0763. Min Act: -0.0002

Data Index: 987774 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0789. Min Act: -0.0001

Data Index: 790976 (C4 (Web Text))

Max Activating Token Index: 847