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

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

Neuron 2202 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: 0.0866. Min Range: -0.0866

Max Act: 0.0843. Min Act: -0.0003

Data Index: 1610438 (Python Code)

Max Activating Token Index: 527

Text #1

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0703. Min Act: -0.0002

Data Index: 767137 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1565699 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0777. Min Act: -0.0003

Data Index: 473717 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1621795 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1464874 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0754. Min Act: -0.0003

Data Index: 710924 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0687. Min Act: -0.0003

Data Index: 102080 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0659. Min Act: -0.0003

Data Index: 834127 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1057368 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0719. Min Act: -0.0003

Data Index: 626950 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1570567 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0731. Min Act: -0.0003

Data Index: 204963 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0720. Min Act: -0.0003

Data Index: 467558 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1414946 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1440748 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1048919 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1537309 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0632. Min Act: -0.0003

Data Index: 1459692 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0704. Min Act: -0.0003

Data Index: 1506257 (Python Code)

Max Activating Token Index: 236