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

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

Neuron 4596 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0002

Data Index: 687050 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1383158 (Python Code)

Max Activating Token Index: 914

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1643135 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0738. Min Act: -0.0002

Data Index: 211380 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1601202 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1096753 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1565798 (Python Code)

Max Activating Token Index: 209

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1566816 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1265444 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1588089 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1496657 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1651116 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1637984 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1460719 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1598011 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1397921 (Python Code)

Max Activating Token Index: 92

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1368581 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1623871 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1431026 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1510856 (Python Code)

Max Activating Token Index: 13