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

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

Neuron 676 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1271914 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 2.0780. Min Range: -2.0780

Max Act: 2.0780. Min Act: -0.0000

Data Index: 374922 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.8433. Min Act: -0.0000

Data Index: 689132 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.9542. Min Act: -0.0000

Data Index: 194396 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.7611. Min Act: -0.0000

Data Index: 151719 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.8426. Min Act: -0.0000

Data Index: 759171 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.7331. Min Act: -0.0000

Data Index: 808819 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1046743 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5757. Min Act: -0.0000

Data Index: 353582 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.7315. Min Act: -0.0000

Data Index: 1076729 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.6630. Min Act: -0.0000

Data Index: 228399 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.6207. Min Act: -0.0000

Data Index: 497392 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.6071. Min Act: -0.0000

Data Index: 815734 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5866. Min Act: -0.0000

Data Index: 223060 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4546. Min Act: -0.0000

Data Index: 151229 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4410. Min Act: -0.0000

Data Index: 448399 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1592697 (Python Code)

Max Activating Token Index: 704

Text #17

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5074. Min Act: -0.0000

Data Index: 182040 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5055. Min Act: -0.0000

Data Index: 312809 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 2.0780. Min Range: -2.0780

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1398285 (Python Code)

Max Activating Token Index: 129