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

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

Neuron 4282 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5648. Min Range: -2.5648

Max Act: 2.5648. Min Act: -0.0000

Data Index: 1196954 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 2.5648. Min Range: -2.5648

Max Act: 2.2169. Min Act: -0.0000

Data Index: 259904 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 2.5648. Min Range: -2.5648

Max Act: 2.2044. Min Act: -0.0000

Data Index: 1180943 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 2.5648. Min Range: -2.5648

Max Act: 2.1568. Min Act: -0.0000

Data Index: 18985 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.9619. Min Act: -0.0000

Data Index: 42756 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.9483. Min Act: -0.0000

Data Index: 1044761 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.9164. Min Act: -0.0000

Data Index: 828324 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.9061. Min Act: 0.0000

Data Index: 1226376 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.8941. Min Act: 0.0000

Data Index: 727851 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1060284 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.8249. Min Act: -0.0000

Data Index: 19106 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.8300. Min Act: -0.0000

Data Index: 83835 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.9350. Min Act: 0.0000

Data Index: 768614 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.7984. Min Act: 0.0000

Data Index: 1266312 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.6738. Min Act: -0.0000

Data Index: 663069 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.7794. Min Act: -0.0000

Data Index: 477335 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.7317. Min Act: -0.0000

Data Index: 616908 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.7546. Min Act: -0.0000

Data Index: 1133304 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.7311. Min Act: -0.0000

Data Index: 1008844 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.5648. Min Range: -2.5648

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1322191 (C4 (Web Text))

Max Activating Token Index: 452