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

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

Neuron 4210 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0829. Min Range: -3.0829

Max Act: 3.0829. Min Act: -0.0001

Data Index: 1554036 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.7640. Min Act: -0.0000

Data Index: 1323337 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.6439. Min Act: -0.0001

Data Index: 1119874 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.5781. Min Act: -0.0000

Data Index: 1225319 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.5607. Min Act: -0.0001

Data Index: 78906 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.5881. Min Act: -0.0001

Data Index: 776396 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1187866 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3890. Min Act: -0.0000

Data Index: 354022 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.5482. Min Act: -0.0001

Data Index: 649434 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.5436. Min Act: -0.0000

Data Index: 1059326 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3423. Min Act: -0.0001

Data Index: 309746 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.1811. Min Act: -0.0000

Data Index: 568894 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3203. Min Act: -0.0000

Data Index: 510709 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.4266. Min Act: -0.0001

Data Index: 48884 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3284. Min Act: -0.0001

Data Index: 969869 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3014. Min Act: -0.0001

Data Index: 1201549 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1315043 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1192282 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3812. Min Act: -0.0000

Data Index: 667088 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 3.0829. Min Range: -3.0829

Max Act: 1.3726. Min Act: -0.0000

Data Index: 41235 (C4 (Web Text))

Max Activating Token Index: 633