Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2299 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1529823 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2064. Min Act: -0.0001

Data Index: 710085 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.2024. Min Act: -0.0001

Data Index: 1432731 (Python Code)

Max Activating Token Index: 457

Text #3

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1594699 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1368562 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1132455 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1169769 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1685. Min Act: -0.0000

Data Index: 501216 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1261090 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1498220 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1384611 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1592975 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1633. Min Act: -0.0000

Data Index: 794504 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1550115 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1326596 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1595043 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1565845 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1586. Min Act: -0.0000

Data Index: 592141 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1069209 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.2313. Min Range: -0.2313

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1550872 (Python Code)

Max Activating Token Index: 786