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

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

Neuron 3053 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3623. Min Range: -2.3623

Max Act: 2.3623. Min Act: -0.0000

Data Index: 363812 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 2.3623. Min Range: -2.3623

Max Act: 2.2569. Min Act: -0.0000

Data Index: 1237673 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 2.3623. Min Range: -2.3623

Max Act: 2.2423. Min Act: -0.0000

Data Index: 789162 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.9710. Min Act: -0.0000

Data Index: 627867 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1091847 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.9741. Min Act: -0.0000

Data Index: 768192 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.7695. Min Act: -0.0000

Data Index: 193201 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.8489. Min Act: -0.0000

Data Index: 1103048 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.6808. Min Act: -0.0000

Data Index: 938310 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.7904. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.7400. Min Act: -0.0000

Data Index: 117413 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.6316. Min Act: -0.0000

Data Index: 158003 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.7137. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.5089. Min Act: -0.0000

Data Index: 248809 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.5561. Min Act: -0.0000

Data Index: 1008405 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.3551. Min Act: -0.0000

Data Index: 1117491 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.3525. Min Act: -0.0000

Data Index: 660403 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1355273 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.3105. Min Act: -0.0000

Data Index: 797271 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 2.3623. Min Range: -2.3623

Max Act: 1.3002. Min Act: -0.0000

Data Index: 763082 (C4 (Web Text))

Max Activating Token Index: 464