Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 922 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.5484. Min Range: -7.5484

Max Act: 7.5484. Min Act: -0.0001

Data Index: 1287918 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.8032. Min Act: -0.0000

Data Index: 849209 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.4684. Min Act: -0.0000

Data Index: 1446770 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.7953. Min Act: -0.0000

Data Index: 1484646 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.7745. Min Act: -0.0001

Data Index: 1467997 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.3932. Min Act: -0.0000

Data Index: 1407507 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 7.5484. Min Range: -7.5484

Max Act: 7.0581. Min Act: -0.0001

Data Index: 319063 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.5239. Min Act: -0.0000

Data Index: 729225 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.6395. Min Act: -0.0000

Data Index: 951500 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.6110. Min Act: -0.0000

Data Index: 1455041 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.6316. Min Act: -0.0000

Data Index: 657241 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.6417. Min Act: -0.0000

Data Index: 1378305 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.5776. Min Act: -0.0000

Data Index: 1555678 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.5998. Min Act: -0.0000

Data Index: 1433342 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.5364. Min Act: -0.0000

Data Index: 1520266 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.7372. Min Act: -0.0000

Data Index: 1483073 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.5563. Min Act: -0.0000

Data Index: 228434 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.3505. Min Act: -0.0000

Data Index: 1264870 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 7.5484. Min Range: -7.5484

Max Act: 6.0991. Min Act: -0.0000

Data Index: 1090770 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 7.5484. Min Range: -7.5484

Max Act: 5.6851. Min Act: -0.0000

Data Index: 212428 (C4 (Web Text))

Max Activating Token Index: 674