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

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

Neuron 4530 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2684. Min Act: -0.0000

Data Index: 785087 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2423. Min Act: -0.0000

Data Index: 166768 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2219. Min Act: -0.0000

Data Index: 429837 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2043. Min Act: -0.0000

Data Index: 708278 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2056. Min Act: -0.0001

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2032. Min Act: -0.0000

Data Index: 349175 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1066670 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1894. Min Act: -0.0000

Data Index: 224383 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1067821 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1788. Min Act: -0.0000

Data Index: 370353 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1181203 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1299. Min Act: -0.0000

Data Index: 313064 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1430. Min Act: -0.0000

Data Index: 436520 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1402. Min Act: -0.0000

Data Index: 767230 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1195. Min Act: -0.0000

Data Index: 67014 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1281. Min Act: -0.0000

Data Index: 685837 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1159. Min Act: -0.0000

Data Index: 193951 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1108. Min Act: -0.0000

Data Index: 586815 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1072. Min Act: -0.0000

Data Index: 738587 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1108. Min Act: -0.0000

Data Index: 822391 (C4 (Web Text))

Max Activating Token Index: 912