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

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

Neuron 4129 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: 0.0721. Min Range: -0.0721

Max Act: 0.0693. Min Act: -0.0002

Data Index: 75795 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0721. Min Act: -0.0002

Data Index: 505595 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1236863 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1388558 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1576066 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1560970 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0669. Min Act: -0.0002

Data Index: 366140 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0656. Min Act: -0.0002

Data Index: 258232 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1628174 (Python Code)

Max Activating Token Index: 937

Text #9

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1554624 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1609330 (Python Code)

Max Activating Token Index: 791

Text #11

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1036880 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1446738 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1400413 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1567889 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0612. Min Act: -0.0002

Data Index: 183361 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0631. Min Act: -0.0002

Data Index: 494492 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0628. Min Act: -0.0002

Data Index: 335444 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0618. Min Act: -0.0002

Data Index: 868384 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1415411 (Python Code)

Max Activating Token Index: 322