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

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

Neuron 1039 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2637. Min Act: -0.0000

Data Index: 976530 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2343. Min Act: -0.0000

Data Index: 181465 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1961. Min Act: -0.0000

Data Index: 651857 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1860. Min Act: -0.0000

Data Index: 990688 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1162683 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1695. Min Act: -0.0000

Data Index: 448429 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1499982 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1714. Min Act: -0.0000

Data Index: 908598 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1220034 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1096801 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1731. Min Act: -0.0000

Data Index: 626045 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1526. Min Act: -0.0000

Data Index: 655032 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1603. Min Act: -0.0000

Data Index: 195709 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1607. Min Act: -0.0000

Data Index: 111602 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1497118 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1611. Min Act: -0.0000

Data Index: 229643 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1548. Min Act: -0.0000

Data Index: 869116 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1635. Min Act: -0.0000

Data Index: 448664 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1613. Min Act: -0.0000

Data Index: 417755 (C4 (Web Text))

Max Activating Token Index: 161