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

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

Neuron 852 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3314. Min Range: -2.3314

Max Act: 2.3314. Min Act: -0.0000

Data Index: 537892 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 2.3314. Min Range: -2.3314

Max Act: 2.2674. Min Act: -0.0000

Data Index: 222415 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.3314. Min Range: -2.3314

Max Act: 2.3084. Min Act: -0.0000

Data Index: 467411 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 2.3314. Min Range: -2.3314

Max Act: 2.1420. Min Act: -0.0000

Data Index: 24235 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 2.3314. Min Range: -2.3314

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1112253 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 2.3314. Min Range: -2.3314

Max Act: 2.1923. Min Act: -0.0000

Data Index: 1080697 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.9711. Min Act: -0.0000

Data Index: 60843 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.9290. Min Act: -0.0000

Data Index: 364969 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.8263. Min Act: -0.0000

Data Index: 497113 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.9161. Min Act: -0.0000

Data Index: 132755 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.7998. Min Act: -0.0000

Data Index: 251723 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.7959. Min Act: -0.0000

Data Index: 388002 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.9052. Min Act: -0.0000

Data Index: 21387 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.6823. Min Act: -0.0000

Data Index: 78007 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.7217. Min Act: -0.0000

Data Index: 1267505 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.7253. Min Act: -0.0000

Data Index: 1128920 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.7020. Min Act: -0.0000

Data Index: 244690 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.8000. Min Act: -0.0000

Data Index: 1045345 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.5566. Min Act: -0.0000

Data Index: 99596 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 2.3314. Min Range: -2.3314

Max Act: 1.7396. Min Act: -0.0000

Data Index: 722991 (C4 (Web Text))

Max Activating Token Index: 467