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

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

Neuron 306 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: 4.6721. Min Range: -4.6721

Max Act: 4.6721. Min Act: -0.0000

Data Index: 124542 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 4.6721. Min Range: -4.6721

Max Act: 4.1908. Min Act: -0.0000

Data Index: 545311 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.3785. Min Act: -0.0000

Data Index: 509761 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.3953. Min Act: -0.0000

Data Index: 1095292 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.3362. Min Act: -0.0000

Data Index: 709553 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.4149. Min Act: -0.0000

Data Index: 964043 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.2128. Min Act: -0.0000

Data Index: 737910 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.1762. Min Act: -0.0000

Data Index: 399194 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.1362. Min Act: -0.0000

Data Index: 1324554 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.2177. Min Act: -0.0000

Data Index: 677624 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.9040. Min Act: -0.0000

Data Index: 1031236 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.2996. Min Act: -0.0000

Data Index: 810096 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.7009. Min Act: -0.0000

Data Index: 652994 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.9523. Min Act: -0.0000

Data Index: 938662 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.9411. Min Act: -0.0000

Data Index: 852364 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 4.6721. Min Range: -4.6721

Max Act: 3.0587. Min Act: -0.0000

Data Index: 953299 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.7536. Min Act: -0.0000

Data Index: 361033 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.8570. Min Act: -0.0000

Data Index: 129940 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.8811. Min Act: -0.0000

Data Index: 290160 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 4.6721. Min Range: -4.6721

Max Act: 2.5551. Min Act: -0.0000

Data Index: 435084 (C4 (Web Text))

Max Activating Token Index: 746