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

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

Neuron 5301 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: 2.5563. Min Range: -2.5563

Max Act: 2.3746. Min Act: -0.0000

Data Index: 843952 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 2.5563. Min Range: -2.5563

Max Act: 2.5563. Min Act: -0.0000

Data Index: 1140363 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 2.5563. Min Range: -2.5563

Max Act: 2.3661. Min Act: -0.0000

Data Index: 262915 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 2.5563. Min Range: -2.5563

Max Act: 2.1199. Min Act: -0.0000

Data Index: 1296870 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 2.5563. Min Range: -2.5563

Max Act: 2.2077. Min Act: -0.0000

Data Index: 748932 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 2.5563. Min Range: -2.5563

Max Act: 2.1493. Min Act: -0.0000

Data Index: 378821 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.8433. Min Act: -0.0000

Data Index: 1203566 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.8515. Min Act: -0.0000

Data Index: 639679 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.9383. Min Act: -0.0000

Data Index: 1200167 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 2.5563. Min Range: -2.5563

Max Act: 2.0105. Min Act: -0.0000

Data Index: 994265 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 2.5563. Min Range: -2.5563

Max Act: 2.0182. Min Act: -0.0000

Data Index: 1118895 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.7663. Min Act: -0.0000

Data Index: 314723 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.8658. Min Act: -0.0000

Data Index: 306362 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1154659 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.8598. Min Act: -0.0000

Data Index: 886332 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.6524. Min Act: -0.0000

Data Index: 582141 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.8290. Min Act: -0.0000

Data Index: 96809 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.7088. Min Act: -0.0000

Data Index: 1251281 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.6219. Min Act: -0.0000

Data Index: 43126 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 2.5563. Min Range: -2.5563

Max Act: 1.8065. Min Act: -0.0000

Data Index: 446564 (C4 (Web Text))

Max Activating Token Index: 215