Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3416 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0002

Data Index: 509774 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0835. Min Act: -0.0002

Data Index: 225961 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0798. Min Act: -0.0002

Data Index: 916550 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1201578 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1030391 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0698. Min Act: -0.0002

Data Index: 366751 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1574595 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1470910 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1059044 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1216250 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1372260 (Python Code)

Max Activating Token Index: 180

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1276571 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0614. Min Act: -0.0002

Data Index: 270998 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1612174 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1510510 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0561. Min Act: -0.0002

Data Index: 892406 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0603. Min Act: -0.0002

Data Index: 281167 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1269712 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1512024 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1380079 (Python Code)

Max Activating Token Index: 274