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

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

Neuron 4754 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.7657. Min Act: -0.0001

Data Index: 590618 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.7177. Min Act: -0.0001

Data Index: 1283854 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6293. Min Act: -0.0001

Data Index: 1565476 (Python Code)

Max Activating Token Index: 309

Text #3

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6232. Min Act: -0.0001

Data Index: 1359554 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6502. Min Act: -0.0001

Data Index: 314060 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.7759. Min Act: -0.0001

Data Index: 1345439 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6191. Min Act: -0.0001

Data Index: 653927 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1568313 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1565831 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6144. Min Act: -0.0001

Data Index: 1067352 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6257. Min Act: -0.0001

Data Index: 1463396 (Python Code)

Max Activating Token Index: 634

Text #11

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6029. Min Act: -0.0001

Data Index: 24371 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6217. Min Act: -0.0001

Data Index: 1186680 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6412. Min Act: -0.0001

Data Index: 50729 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6236. Min Act: -0.0001

Data Index: 802713 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6594. Min Act: -0.0001

Data Index: 227392 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5958. Min Act: -0.0001

Data Index: 1010432 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5788. Min Act: -0.0001

Data Index: 567776 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1255855 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6533. Min Act: -0.0001

Data Index: 706903 (C4 (Web Text))

Max Activating Token Index: 251