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

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

Neuron 5320 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: 2.1579. Min Range: -2.1579

Max Act: 2.1579. Min Act: -0.0000

Data Index: 1131863 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 2.1579. Min Range: -2.1579

Max Act: 2.0386. Min Act: -0.0000

Data Index: 524487 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 2.1579. Min Range: -2.1579

Max Act: 2.1351. Min Act: -0.0000

Data Index: 76175 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1340679 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 2.1579. Min Range: -2.1579

Max Act: 2.0739. Min Act: -0.0000

Data Index: 56367 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.8417. Min Act: -0.0000

Data Index: 565172 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.9456. Min Act: -0.0000

Data Index: 426152 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.9688. Min Act: -0.0000

Data Index: 1233796 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.6526. Min Act: -0.0000

Data Index: 451784 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.7575. Min Act: -0.0000

Data Index: 326453 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.6412. Min Act: -0.0000

Data Index: 948882 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.8444. Min Act: -0.0000

Data Index: 956564 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.8419. Min Act: -0.0000

Data Index: 991759 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.8216. Min Act: -0.0000

Data Index: 478018 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.5859. Min Act: -0.0000

Data Index: 304147 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.7912. Min Act: -0.0000

Data Index: 173991 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.8404. Min Act: -0.0000

Data Index: 437284 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.6126. Min Act: -0.0000

Data Index: 628942 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.6911. Min Act: -0.0000

Data Index: 901624 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 2.1579. Min Range: -2.1579

Max Act: 1.5683. Min Act: -0.0000

Data Index: 417231 (C4 (Web Text))

Max Activating Token Index: 906