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

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

Neuron 1979 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: 0.6938. Min Range: -0.6938

Max Act: 0.6938. Min Act: -0.0000

Data Index: 744894 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.6018. Min Act: -0.0000

Data Index: 756767 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5554. Min Act: -0.0000

Data Index: 564072 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1316973 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5732. Min Act: -0.0000

Data Index: 410766 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1061367 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5679. Min Act: -0.0000

Data Index: 319096 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5481. Min Act: -0.0000

Data Index: 101292 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5044. Min Act: -0.0000

Data Index: 970547 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5334. Min Act: -0.0000

Data Index: 632392 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1175632 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5327. Min Act: -0.0000

Data Index: 773091 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4978. Min Act: -0.0000

Data Index: 785568 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4713. Min Act: -0.0000

Data Index: 535782 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1219555 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4486. Min Act: -0.0000

Data Index: 544627 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1208212 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4508. Min Act: -0.0000

Data Index: 96693 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4616. Min Act: -0.0000

Data Index: 856775 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4446. Min Act: -0.0000

Data Index: 743656 (C4 (Web Text))

Max Activating Token Index: 885