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

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

Neuron 3880 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1055929 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.3147. Min Act: -0.0000

Data Index: 361069 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1112202 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.2009. Min Act: -0.0000

Data Index: 239693 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.2633. Min Act: -0.0000

Data Index: 893468 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.0605. Min Act: -0.0000

Data Index: 102041 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1160098 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1959. Min Act: -0.0000

Data Index: 664829 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1199015 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.2168. Min Act: -0.0000

Data Index: 895446 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1697. Min Act: -0.0000

Data Index: 742759 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1891. Min Act: -0.0000

Data Index: 774777 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.0265. Min Act: -0.0000

Data Index: 883269 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.0872. Min Act: -0.0000

Data Index: 503584 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1084. Min Act: -0.0000

Data Index: 627695 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.0323. Min Act: -0.0000

Data Index: 978280 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1178156 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1243722 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.0370. Min Act: -0.0000

Data Index: 54812 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.0503. Min Act: -0.0000

Data Index: 538965 (C4 (Web Text))

Max Activating Token Index: 648