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

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

Neuron 4516 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: 1.0272. Min Range: -1.0272

Max Act: 1.0272. Min Act: -0.0000

Data Index: 990576 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0219. Min Act: -0.0000

Data Index: 336828 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0121. Min Act: -0.0000

Data Index: 288643 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9963. Min Act: -0.0000

Data Index: 673235 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9487. Min Act: -0.0000

Data Index: 954267 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1144853 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9445. Min Act: -0.0000

Data Index: 963432 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1067868 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8817. Min Act: -0.0000

Data Index: 1109494 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8829. Min Act: -0.0000

Data Index: 727280 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9056. Min Act: -0.0000

Data Index: 939787 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8825. Min Act: -0.0000

Data Index: 752105 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9000. Min Act: -0.0000

Data Index: 421331 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8594. Min Act: -0.0000

Data Index: 506942 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8819. Min Act: -0.0000

Data Index: 773543 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1233238 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8765. Min Act: -0.0000

Data Index: 480902 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8839. Min Act: -0.0000

Data Index: 422985 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9058. Min Act: -0.0000

Data Index: 294196 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9057. Min Act: -0.0000

Data Index: 898482 (C4 (Web Text))

Max Activating Token Index: 586