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

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

Neuron 5823 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.9770. Min Act: -0.0000

Data Index: 223081 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.8072. Min Act: -0.0000

Data Index: 247762 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.7655. Min Act: -0.0000

Data Index: 147277 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.7391. Min Act: -0.0000

Data Index: 459768 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.5168. Min Act: -0.0000

Data Index: 1147152 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.6380. Min Act: -0.0000

Data Index: 774848 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.7241. Min Act: -0.0000

Data Index: 768349 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.7112. Min Act: -0.0000

Data Index: 543050 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.5168. Min Act: -0.0000

Data Index: 441305 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.5332. Min Act: -0.0000

Data Index: 511433 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.5787. Min Act: -0.0000

Data Index: 26215 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.4913. Min Act: -0.0000

Data Index: 688760 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1154252 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.4712. Min Act: -0.0000

Data Index: 113501 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.3976. Min Act: -0.0000

Data Index: 216681 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.5211. Min Act: -0.0000

Data Index: 1212185 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.4971. Min Act: -0.0000

Data Index: 140241 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.5292. Min Act: -0.0000

Data Index: 895410 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.4684. Min Act: -0.0000

Data Index: 662939 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 2.9770. Min Range: -2.9770

Max Act: 2.3950. Min Act: -0.0000

Data Index: 1176339 (C4 (Web Text))

Max Activating Token Index: 670