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

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

Neuron 4273 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: 0.6756. Min Range: -0.6756

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1483449 (Python Code)

Max Activating Token Index: 1009

Text #1

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1591753 (Python Code)

Max Activating Token Index: 203

Text #2

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.6187. Min Act: -0.0001

Data Index: 916460 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5837. Min Act: -0.0001

Data Index: 293744 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1422741 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5694. Min Act: -0.0001

Data Index: 1148191 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5785. Min Act: -0.0001

Data Index: 241753 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1070756 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5871. Min Act: -0.0001

Data Index: 1474879 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1207604 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1045969 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5446. Min Act: -0.0001

Data Index: 1006219 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5180. Min Act: -0.0001

Data Index: 1636630 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1540045 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5351. Min Act: -0.0001

Data Index: 1170478 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5881. Min Act: -0.0001

Data Index: 213042 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5256. Min Act: -0.0001

Data Index: 1489903 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.4785. Min Act: -0.0001

Data Index: 723725 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5238. Min Act: -0.0001

Data Index: 1130316 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.6756. Min Range: -0.6756

Max Act: 0.5251. Min Act: -0.0001

Data Index: 1557202 (Python Code)

Max Activating Token Index: 617