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

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

Neuron 856 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: 1.8791. Min Range: -1.8791

Max Act: 1.8791. Min Act: -0.0000

Data Index: 357521 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.5917. Min Act: -0.0000

Data Index: 172264 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.3881. Min Act: -0.0000

Data Index: 347101 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.3229. Min Act: -0.0000

Data Index: 819922 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.3158. Min Act: -0.0000

Data Index: 236048 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1271278 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2983. Min Act: -0.0000

Data Index: 522792 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.3651. Min Act: -0.0000

Data Index: 584482 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.3281. Min Act: -0.0000

Data Index: 40337 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2751. Min Act: -0.0000

Data Index: 89992 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.3398. Min Act: -0.0000

Data Index: 157000 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2908. Min Act: -0.0000

Data Index: 262089 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2610. Min Act: -0.0000

Data Index: 329068 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2169. Min Act: -0.0000

Data Index: 282643 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2746. Min Act: -0.0000

Data Index: 945164 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.1918. Min Act: -0.0000

Data Index: 942732 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2167. Min Act: -0.0000

Data Index: 496488 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1148016 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2458. Min Act: -0.0000

Data Index: 858449 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.8791. Min Range: -1.8791

Max Act: 1.2364. Min Act: -0.0000

Data Index: 424229 (C4 (Web Text))

Max Activating Token Index: 649