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

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

Neuron 3118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.2688. Min Act: -0.0002

Data Index: 92355 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.2345. Min Act: -0.0002

Data Index: 106202 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.2191. Min Act: -0.0002

Data Index: 1057120 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.2075. Min Act: -0.0002

Data Index: 498601 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.2496. Min Act: -0.0002

Data Index: 825938 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.2058. Min Act: -0.0002

Data Index: 828993 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1409. Min Act: -0.0002

Data Index: 13412 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1683. Min Act: -0.0002

Data Index: 344549 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1389. Min Act: -0.0002

Data Index: 1231264 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.0922. Min Act: -0.0002

Data Index: 1317039 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1477. Min Act: -0.0002

Data Index: 227015 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1474. Min Act: -0.0002

Data Index: 381504 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1749. Min Act: -0.0002

Data Index: 790542 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1646. Min Act: -0.0002

Data Index: 1170134 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1750. Min Act: -0.0002

Data Index: 737355 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1070. Min Act: -0.0002

Data Index: 1151972 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.0556. Min Act: -0.0002

Data Index: 165098 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1294. Min Act: -0.0002

Data Index: 521514 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.0866. Min Act: -0.0002

Data Index: 75294 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.2688. Min Range: -1.2688

Max Act: 1.1477. Min Act: -0.0002

Data Index: 1084393 (C4 (Web Text))

Max Activating Token Index: 43