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

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

Neuron 878 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: 0.2345. Min Range: -0.2345

Max Act: 0.2345. Min Act: -0.0006

Data Index: 483869 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2309. Min Act: -0.0006

Data Index: 264290 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2123. Min Act: -0.0006

Data Index: 700375 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2203. Min Act: -0.0006

Data Index: 433104 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1857. Min Act: -0.0006

Data Index: 1184463 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2054. Min Act: -0.0006

Data Index: 903549 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2188. Min Act: -0.0006

Data Index: 1139804 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1941. Min Act: -0.0006

Data Index: 363043 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1971. Min Act: -0.0006

Data Index: 968182 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2020. Min Act: -0.0006

Data Index: 1342298 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1937. Min Act: -0.0006

Data Index: 126297 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1926. Min Act: -0.0006

Data Index: 494669 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1996. Min Act: -0.0006

Data Index: 854562 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2074. Min Act: -0.0006

Data Index: 893696 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1985. Min Act: -0.0006

Data Index: 328131 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1893. Min Act: -0.0006

Data Index: 886129 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1819. Min Act: -0.0006

Data Index: 170366 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2108. Min Act: -0.0006

Data Index: 1037814 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1926. Min Act: -0.0006

Data Index: 1063708 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1919. Min Act: -0.0006

Data Index: 665489 (C4 (Web Text))

Max Activating Token Index: 19