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

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

Neuron 1912 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: 0.1097. Min Range: -0.1097

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1640006 (Python Code)

Max Activating Token Index: 357

Text #1

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1470261 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1455297 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1628053 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1610735 (Python Code)

Max Activating Token Index: 836

Text #5

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1432166 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1563781 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1392151 (Python Code)

Max Activating Token Index: 280

Text #8

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0743. Min Act: -0.0002

Data Index: 467754 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1574292 (Python Code)

Max Activating Token Index: 703

Text #10

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0725. Min Act: -0.0002

Data Index: 408676 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1539504 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0748. Min Act: -0.0002

Data Index: 541766 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0699. Min Act: -0.0002

Data Index: 330563 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1502308 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1363769 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1587290 (Python Code)

Max Activating Token Index: 632

Text #17

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0664. Min Act: -0.0002

Data Index: 658964 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1576694 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1482488 (Python Code)

Max Activating Token Index: 156