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

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

Neuron 2216 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.9213. Min Act: -0.0000

Data Index: 339388 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.9173. Min Act: -0.0000

Data Index: 331225 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.8107. Min Act: -0.0000

Data Index: 933895 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7542. Min Act: -0.0000

Data Index: 248003 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7751. Min Act: -0.0000

Data Index: 479309 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7132. Min Act: -0.0000

Data Index: 628181 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7070. Min Act: -0.0000

Data Index: 30152 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6927. Min Act: -0.0000

Data Index: 809133 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6784. Min Act: -0.0000

Data Index: 949771 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1099619 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1020948 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1566028 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6781. Min Act: -0.0000

Data Index: 818205 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6670. Min Act: 0.0000

Data Index: 231342 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6671. Min Act: -0.0000

Data Index: 338371 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6580. Min Act: -0.0000

Data Index: 979699 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1317801 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1413390 (Python Code)

Max Activating Token Index: 455

Text #18

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.5850. Min Act: -0.0000

Data Index: 697180 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.9213. Min Range: -0.9213

Max Act: 0.5781. Min Act: -0.0000

Data Index: 290574 (C4 (Web Text))

Max Activating Token Index: 822