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

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

Neuron 4062 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.6804. Min Act: -0.0000

Data Index: 1045918 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.2663. Min Act: -0.0000

Data Index: 734685 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.2308. Min Act: -0.0000

Data Index: 1055160 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.1935. Min Act: -0.0000

Data Index: 386830 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.3875. Min Act: -0.0000

Data Index: 827586 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.1496. Min Act: -0.0000

Data Index: 881675 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.1482. Min Act: -0.0000

Data Index: 1136812 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.1255. Min Act: -0.0000

Data Index: 215723 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.1152. Min Act: -0.0000

Data Index: 816361 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.0831. Min Act: -0.0000

Data Index: 313184 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.0700. Min Act: -0.0000

Data Index: 1213147 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.0608. Min Act: -0.0000

Data Index: 643039 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.0290. Min Act: -0.0000

Data Index: 1273464 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.0400. Min Act: -0.0000

Data Index: 1086614 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 2.6804. Min Range: -2.6804

Max Act: 1.9182. Min Act: -0.0000

Data Index: 1542992 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 2.6804. Min Range: -2.6804

Max Act: 1.9988. Min Act: -0.0000

Data Index: 1135176 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 2.6804. Min Range: -2.6804

Max Act: 1.9009. Min Act: -0.0000

Data Index: 1236619 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 2.6804. Min Range: -2.6804

Max Act: 1.9897. Min Act: -0.0000

Data Index: 846437 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 2.6804. Min Range: -2.6804

Max Act: 2.0920. Min Act: -0.0000

Data Index: 759108 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 2.6804. Min Range: -2.6804

Max Act: 1.8649. Min Act: -0.0000

Data Index: 767973 (C4 (Web Text))

Max Activating Token Index: 397