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

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

Neuron 2899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1576850 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6794. Min Act: -0.0000

Data Index: 989049 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6732. Min Act: -0.0000

Data Index: 755283 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6023. Min Act: -0.0000

Data Index: 565115 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5746. Min Act: -0.0000

Data Index: 661676 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1579374 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5609. Min Act: -0.0000

Data Index: 898776 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1301247 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1481077 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1565501 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5506. Min Act: -0.0000

Data Index: 618565 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1320383 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1445157 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1358200 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5564. Min Act: -0.0000

Data Index: 794615 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1005300 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5494. Min Act: -0.0000

Data Index: 345135 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5110. Min Act: -0.0000

Data Index: 333626 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5252. Min Act: -0.0000

Data Index: 853784 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.7779. Min Range: -0.7779

Max Act: 0.5415. Min Act: -0.0000

Data Index: 66151 (C4 (Web Text))

Max Activating Token Index: 548