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

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

Neuron 3778 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7036. Min Act: -0.0001

Data Index: 1038538 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7778. Min Act: -0.0001

Data Index: 857093 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7632. Min Act: -0.0001

Data Index: 51873 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.6876. Min Act: -0.0001

Data Index: 26627 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.5698. Min Act: -0.0001

Data Index: 60761 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.6326. Min Act: -0.0001

Data Index: 443433 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.4544. Min Act: -0.0001

Data Index: 701193 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.5125. Min Act: -0.0001

Data Index: 452304 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3890. Min Act: -0.0001

Data Index: 403908 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3180. Min Act: -0.0001

Data Index: 379493 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.4199. Min Act: -0.0001

Data Index: 888530 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2209. Min Act: -0.0001

Data Index: 1192729 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.3213. Min Act: -0.0001

Data Index: 769917 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.4935. Min Act: -0.0001

Data Index: 1091325 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.4527. Min Act: -0.0001

Data Index: 1210197 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.4995. Min Act: -0.0001

Data Index: 1034837 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2488. Min Act: -0.0001

Data Index: 598405 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2361. Min Act: -0.0001

Data Index: 678446 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2726. Min Act: -0.0001

Data Index: 462733 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.2838. Min Act: -0.0001

Data Index: 708651 (C4 (Web Text))

Max Activating Token Index: 995