Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 251 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.6829. Min Act: -0.0006

Data Index: 1006641 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.4042. Min Act: -0.0006

Data Index: 15777 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.3462. Min Act: -0.0006

Data Index: 868627 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2747. Min Act: -0.0006

Data Index: 1198734 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.3666. Min Act: -0.0006

Data Index: 396883 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2074. Min Act: -0.0006

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2892. Min Act: -0.0006

Data Index: 1303912 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.3079. Min Act: -0.0006

Data Index: 491728 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2655. Min Act: -0.0006

Data Index: 1174096 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2588. Min Act: -0.0006

Data Index: 586025 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2517. Min Act: -0.0006

Data Index: 1272129 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2385. Min Act: -0.0005

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2262. Min Act: -0.0006

Data Index: 549713 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.3036. Min Act: -0.0006

Data Index: 767866 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2245. Min Act: -0.0006

Data Index: 567228 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2393. Min Act: -0.0006

Data Index: 1271747 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2646. Min Act: -0.0006

Data Index: 540609 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.1298. Min Act: -0.0006

Data Index: 433411 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.1305. Min Act: -0.0006

Data Index: 322034 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.6829. Min Range: -1.6829

Max Act: 1.2412. Min Act: -0.0006

Data Index: 285737 (C4 (Web Text))

Max Activating Token Index: 139