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

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

Neuron 933 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1073. Min Range: -1.1073

Max Act: 1.1073. Min Act: -0.0000

Data Index: 374540 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.1073. Min Range: -1.1073

Max Act: 1.0292. Min Act: -0.0000

Data Index: 39691 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 1.1073. Min Range: -1.1073

Max Act: 1.0076. Min Act: -0.0000

Data Index: 954488 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9751. Min Act: -0.0000

Data Index: 263404 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 1.1073. Min Range: -1.1073

Max Act: 1.0144. Min Act: -0.0000

Data Index: 298631 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1122583 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.1073. Min Range: -1.1073

Max Act: 1.0316. Min Act: -0.0000

Data Index: 434980 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1585616 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1192106 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8003. Min Act: -0.0000

Data Index: 125996 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8991. Min Act: -0.0000

Data Index: 303381 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9219. Min Act: -0.0000

Data Index: 966149 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8482. Min Act: -0.0000

Data Index: 962078 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9180. Min Act: -0.0000

Data Index: 904844 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8888. Min Act: -0.0000

Data Index: 627003 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8920. Min Act: -0.0000

Data Index: 520949 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.7830. Min Act: -0.0000

Data Index: 419862 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1235134 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8343. Min Act: -0.0000

Data Index: 521111 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1199893 (C4 (Web Text))

Max Activating Token Index: 429