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

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

Neuron 3524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9923. Min Act: -0.0000

Data Index: 876559 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.0548. Min Range: -1.0548

Max Act: 1.0548. Min Act: -0.0000

Data Index: 140323 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 1.0548. Min Range: -1.0548

Max Act: 1.0158. Min Act: -0.0000

Data Index: 191128 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1450866 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1650449 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9515. Min Act: -0.0000

Data Index: 229682 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1380891 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1526417 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9351. Min Act: -0.0000

Data Index: 1127628 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1632138 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1654025 (Python Code)

Max Activating Token Index: 821

Text #11

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1460574 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1569681 (Python Code)

Max Activating Token Index: 443

Text #13

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1499765 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1539445 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1639756 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8864. Min Act: -0.0000

Data Index: 145039 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8630. Min Act: -0.0000

Data Index: 539299 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1650962 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1478986 (Python Code)

Max Activating Token Index: 946