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

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

Neuron 647 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: 0.5132. Min Range: -0.5132

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1174484 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1319139 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1159592 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1268357 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3982. Min Act: -0.0000

Data Index: 77554 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3760. Min Act: -0.0000

Data Index: 18506 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3660. Min Act: -0.0000

Data Index: 555961 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1164358 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3449. Min Act: -0.0000

Data Index: 166241 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3369. Min Act: -0.0000

Data Index: 649948 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3572. Min Act: -0.0000

Data Index: 639983 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3505. Min Act: -0.0000

Data Index: 107666 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1332377 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3203. Min Act: -0.0000

Data Index: 828886 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3231. Min Act: -0.0000

Data Index: 555701 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1303930 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1197046 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3050. Min Act: -0.0000

Data Index: 873917 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3010. Min Act: -0.0000

Data Index: 668297 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.2992. Min Act: -0.0000

Data Index: 852435 (C4 (Web Text))

Max Activating Token Index: 446