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

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

Neuron 2314 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: 2.6002. Min Range: -2.6002

Max Act: 2.4608. Min Act: -0.0000

Data Index: 259787 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.5303. Min Act: -0.0000

Data Index: 465317 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.3949. Min Act: -0.0000

Data Index: 1436153 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.1846. Min Act: -0.0000

Data Index: 1426710 (Python Code)

Max Activating Token Index: 668

Text #4

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.3629. Min Act: -0.0000

Data Index: 1502122 (Python Code)

Max Activating Token Index: 409

Text #5

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.6002. Min Act: -0.0000

Data Index: 1063947 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.2031. Min Act: -0.0000

Data Index: 1601753 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.1618. Min Act: -0.0000

Data Index: 848639 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.1481. Min Act: -0.0000

Data Index: 739818 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.3115. Min Act: -0.0000

Data Index: 1435263 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 2.6002. Min Range: -2.6002

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1137095 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.0787. Min Act: -0.0000

Data Index: 394570 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 2.6002. Min Range: -2.6002

Max Act: 1.9488. Min Act: -0.0000

Data Index: 254151 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 2.6002. Min Range: -2.6002

Max Act: 1.8408. Min Act: -0.0000

Data Index: 1247587 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.0448. Min Act: -0.0000

Data Index: 1558279 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 2.6002. Min Range: -2.6002

Max Act: 2.0232. Min Act: -0.0000

Data Index: 1285387 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 2.6002. Min Range: -2.6002

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1499683 (Python Code)

Max Activating Token Index: 797

Text #17

Max Range: 2.6002. Min Range: -2.6002

Max Act: 1.9001. Min Act: -0.0000

Data Index: 823131 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 2.6002. Min Range: -2.6002

Max Act: 1.9745. Min Act: -0.0000

Data Index: 1204156 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 2.6002. Min Range: -2.6002

Max Act: 1.9712. Min Act: -0.0000

Data Index: 463100 (C4 (Web Text))

Max Activating Token Index: 439