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

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

Neuron 5139 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1835. Min Range: -6.1835

Max Act: 6.1835. Min Act: -0.0000

Data Index: 578940 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.9529. Min Act: -0.0000

Data Index: 250978 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.7252. Min Act: -0.0000

Data Index: 1305201 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.5570. Min Act: -0.0000

Data Index: 665984 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.2438. Min Act: -0.0000

Data Index: 615826 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.2753. Min Act: -0.0000

Data Index: 899780 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.0994. Min Act: -0.0000

Data Index: 1115803 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.6765. Min Act: -0.0000

Data Index: 160373 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.0616. Min Act: -0.0000

Data Index: 1191194 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 6.1835. Min Range: -6.1835

Max Act: 5.1838. Min Act: -0.0000

Data Index: 1005636 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.9840. Min Act: -0.0000

Data Index: 487975 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.1860. Min Act: -0.0000

Data Index: 1268699 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.9689. Min Act: -0.0000

Data Index: 678487 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.6183. Min Act: -0.0000

Data Index: 1135997 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.7801. Min Act: -0.0000

Data Index: 994542 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.8573. Min Act: -0.0000

Data Index: 868459 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.5212. Min Act: -0.0000

Data Index: 803569 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.5498. Min Act: -0.0000

Data Index: 201405 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.6774. Min Act: -0.0000

Data Index: 1163052 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 6.1835. Min Range: -6.1835

Max Act: 4.4581. Min Act: -0.0000

Data Index: 365241 (C4 (Web Text))

Max Activating Token Index: 188