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

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

Neuron 821 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4521. Min Range: -1.4521

Max Act: 1.4521. Min Act: -0.0000

Data Index: 579343 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.4521. Min Range: -1.4521

Max Act: 1.3176. Min Act: -0.0000

Data Index: 366779 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.4521. Min Range: -1.4521

Max Act: 1.0468. Min Act: -0.0000

Data Index: 403617 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.4521. Min Range: -1.4521

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1231833 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.4521. Min Range: -1.4521

Max Act: 1.0266. Min Act: -0.0000

Data Index: 374673 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.9629. Min Act: -0.0000

Data Index: 221049 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1601561 (Python Code)

Max Activating Token Index: 179

Text #7

Max Range: 1.4521. Min Range: -1.4521

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1276205 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.9553. Min Act: -0.0000

Data Index: 359459 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.8468. Min Act: -0.0000

Data Index: 345885 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.8566. Min Act: -0.0000

Data Index: 610974 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.8728. Min Act: -0.0000

Data Index: 727483 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1041803 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.7604. Min Act: -0.0000

Data Index: 292686 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.8354. Min Act: -0.0000

Data Index: 208620 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.7860. Min Act: -0.0000

Data Index: 274211 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.7239. Min Act: -0.0000

Data Index: 406550 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1419014 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.7550. Min Act: -0.0000

Data Index: 444785 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.4521. Min Range: -1.4521

Max Act: 0.7288. Min Act: -0.0000

Data Index: 664566 (C4 (Web Text))

Max Activating Token Index: 946