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

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

Neuron 965 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4216. Min Range: -2.4216

Max Act: 2.4216. Min Act: -0.0000

Data Index: 1400726 (Python Code)

Max Activating Token Index: 792

Text #1

Max Range: 2.4216. Min Range: -2.4216

Max Act: 2.2124. Min Act: -0.0000

Data Index: 1553453 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 2.4216. Min Range: -2.4216

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1508764 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 2.4216. Min Range: -2.4216

Max Act: 2.1623. Min Act: -0.0000

Data Index: 1609408 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 2.4216. Min Range: -2.4216

Max Act: 2.0220. Min Act: -0.0000

Data Index: 1440683 (Python Code)

Max Activating Token Index: 484

Text #5

Max Range: 2.4216. Min Range: -2.4216

Max Act: 2.0103. Min Act: -0.0000

Data Index: 1506857 (Python Code)

Max Activating Token Index: 465

Text #6

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.9622. Min Act: -0.0000

Data Index: 1208398 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.7940. Min Act: -0.0000

Data Index: 604666 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.7971. Min Act: -0.0000

Data Index: 1619385 (Python Code)

Max Activating Token Index: 623

Text #9

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.6806. Min Act: -0.0000

Data Index: 121588 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.7797. Min Act: -0.0000

Data Index: 85332 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.8586. Min Act: -0.0000

Data Index: 347081 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1482379 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.7806. Min Act: -0.0000

Data Index: 805356 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.7676. Min Act: -0.0000

Data Index: 1518520 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.5744. Min Act: -0.0000

Data Index: 766953 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.7393. Min Act: -0.0000

Data Index: 1616846 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.7639. Min Act: -0.0000

Data Index: 1376446 (Python Code)

Max Activating Token Index: 933

Text #18

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.6532. Min Act: -0.0000

Data Index: 128624 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 2.4216. Min Range: -2.4216

Max Act: 1.6254. Min Act: -0.0000

Data Index: 614464 (C4 (Web Text))

Max Activating Token Index: 300