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

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

Neuron 4065 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: 0.2356. Min Range: -0.2356

Max Act: 0.2320. Min Act: -0.0000

Data Index: 189506 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1215953 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2356. Min Act: -0.0000

Data Index: 906625 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2145. Min Act: -0.0000

Data Index: 390094 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.2062. Min Act: -0.0000

Data Index: 69862 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1889. Min Act: -0.0000

Data Index: 942028 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1874. Min Act: -0.0000

Data Index: 695986 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1855. Min Act: -0.0000

Data Index: 536556 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1781. Min Act: -0.0000

Data Index: 166444 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1837. Min Act: -0.0000

Data Index: 331470 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1750. Min Act: -0.0000

Data Index: 187240 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1764. Min Act: -0.0000

Data Index: 816789 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1758. Min Act: -0.0000

Data Index: 955951 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1693. Min Act: -0.0000

Data Index: 265979 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1754. Min Act: -0.0000

Data Index: 357458 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1718. Min Act: -0.0000

Data Index: 528077 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1662. Min Act: -0.0000

Data Index: 979122 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1708. Min Act: -0.0000

Data Index: 468104 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1039056 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.2356. Min Range: -0.2356

Max Act: 0.1613. Min Act: -0.0000

Data Index: 145889 (C4 (Web Text))

Max Activating Token Index: 824