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

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

Neuron 2788 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: 4.7592. Min Range: -4.7592

Max Act: 4.7592. Min Act: -0.0000

Data Index: 182006 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 4.7592. Min Range: -4.7592

Max Act: 4.3400. Min Act: -0.0000

Data Index: 189739 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 4.7592. Min Range: -4.7592

Max Act: 4.2773. Min Act: -0.0000

Data Index: 974996 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 4.7592. Min Range: -4.7592

Max Act: 4.0723. Min Act: -0.0000

Data Index: 1347514 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.9175. Min Act: -0.0000

Data Index: 188132 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.5607. Min Act: -0.0000

Data Index: 435850 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.7379. Min Act: -0.0000

Data Index: 75530 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.8836. Min Act: -0.0000

Data Index: 92055 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.7380. Min Act: -0.0000

Data Index: 350197 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.1348. Min Act: -0.0000

Data Index: 468505 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.6134. Min Act: -0.0000

Data Index: 231527 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.5714. Min Act: -0.0000

Data Index: 1220234 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.5498. Min Act: -0.0000

Data Index: 1139531 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.3832. Min Act: -0.0000

Data Index: 1052497 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.7579. Min Act: -0.0000

Data Index: 564873 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.4377. Min Act: -0.0000

Data Index: 1289001 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.1180. Min Act: -0.0000

Data Index: 343588 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.3883. Min Act: -0.0000

Data Index: 49570 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.3784. Min Act: -0.0000

Data Index: 554426 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 4.7592. Min Range: -4.7592

Max Act: 3.2271. Min Act: -0.0000

Data Index: 30957 (C4 (Web Text))

Max Activating Token Index: 894