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

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

Neuron 2075 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: 1.2945. Min Range: -1.2945

Max Act: 1.2945. Min Act: -0.0000

Data Index: 989991 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0770. Min Act: -0.0000

Data Index: 703543 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1308. Min Act: -0.0000

Data Index: 78881 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1298759 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1585. Min Act: -0.0000

Data Index: 953821 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1177. Min Act: -0.0000

Data Index: 156821 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1040. Min Act: -0.0000

Data Index: 466867 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1235. Min Act: -0.0000

Data Index: 656857 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1371. Min Act: -0.0000

Data Index: 373826 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1162. Min Act: -0.0000

Data Index: 764652 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0646. Min Act: -0.0000

Data Index: 627808 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0503. Min Act: -0.0000

Data Index: 370700 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1070957 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1239. Min Act: -0.0000

Data Index: 657747 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1068145 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0884. Min Act: -0.0000

Data Index: 942722 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1106209 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1097. Min Act: -0.0000

Data Index: 158788 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0800. Min Act: -0.0000

Data Index: 9877 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0775. Min Act: -0.0000

Data Index: 643550 (C4 (Web Text))

Max Activating Token Index: 730