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

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

Neuron 1750 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: 0.2207. Min Range: -0.2207

Max Act: 0.2207. Min Act: -0.0000

Data Index: 374780 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.2034. Min Act: -0.0000

Data Index: 73496 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1771. Min Act: -0.0000

Data Index: 670918 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1800. Min Act: -0.0000

Data Index: 60175 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1856. Min Act: -0.0000

Data Index: 687639 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1293822 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1738. Min Act: -0.0000

Data Index: 560237 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1785. Min Act: -0.0001

Data Index: 377760 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1760. Min Act: -0.0000

Data Index: 398210 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1729. Min Act: -0.0000

Data Index: 192429 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1579. Min Act: -0.0000

Data Index: 742413 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1064719 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1684. Min Act: -0.0000

Data Index: 39293 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1502. Min Act: -0.0000

Data Index: 8032 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1538. Min Act: -0.0000

Data Index: 349588 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1558. Min Act: -0.0000

Data Index: 707816 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1128907 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1620. Min Act: -0.0000

Data Index: 693323 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1481. Min Act: -0.0000

Data Index: 502216 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1455. Min Act: -0.0000

Data Index: 380857 (C4 (Web Text))

Max Activating Token Index: 622