Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 14 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0671. Min Range: -1.0671

Max Act: 1.0671. Min Act: -0.0000

Data Index: 110443 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.9926. Min Act: -0.0000

Data Index: 8544 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 1.0671. Min Range: -1.0671

Max Act: 1.0007. Min Act: -0.0000

Data Index: 804226 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.9364. Min Act: -0.0000

Data Index: 907757 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7802. Min Act: -0.0000

Data Index: 443566 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1199556 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7944. Min Act: -0.0000

Data Index: 383930 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7945. Min Act: -0.0000

Data Index: 221594 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.8417. Min Act: -0.0000

Data Index: 331819 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7924. Min Act: -0.0000

Data Index: 981873 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1028856 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1038541 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7643. Min Act: -0.0000

Data Index: 436723 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7426. Min Act: -0.0000

Data Index: 444872 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7422. Min Act: -0.0000

Data Index: 898765 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.8101. Min Act: -0.0000

Data Index: 276830 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7250. Min Act: -0.0000

Data Index: 496620 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1290231 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1133307 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.0671. Min Range: -1.0671

Max Act: 0.6775. Min Act: -0.0000

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 230