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

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

Neuron 682 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.6040. Min Act: -0.0000

Data Index: 1478330 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1413074 (Python Code)

Max Activating Token Index: 469

Text #2

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1399355 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1443497 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2803. Min Act: -0.0000

Data Index: 486508 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1596890 (Python Code)

Max Activating Token Index: 563

Text #6

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2303. Min Act: 0.0000

Data Index: 1564940 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1619747 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2206. Min Act: -0.0000

Data Index: 1449976 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.1802. Min Act: -0.0000

Data Index: 704904 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1448964 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1398425 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1516449 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1437865 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1649227 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1538264 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1394526 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1513239 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.9282. Min Act: -0.0000

Data Index: 237590 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1465308 (Python Code)

Max Activating Token Index: 848