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

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

Neuron 2315 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.9698. Min Act: -0.0002

Data Index: 526830 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7319. Min Act: -0.0002

Data Index: 371478 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7062. Min Act: -0.0003

Data Index: 107046 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7153. Min Act: -0.0002

Data Index: 719562 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7147. Min Act: -0.0002

Data Index: 142156 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7078. Min Act: -0.0002

Data Index: 1025445 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7031. Min Act: -0.0002

Data Index: 322826 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6691. Min Act: -0.0003

Data Index: 437594 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6886. Min Act: -0.0002

Data Index: 94540 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6804. Min Act: -0.0003

Data Index: 71425 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.7120. Min Act: -0.0003

Data Index: 1260459 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6657. Min Act: -0.0002

Data Index: 1159396 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6404. Min Act: -0.0003

Data Index: 15564 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6781. Min Act: -0.0003

Data Index: 960793 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6482. Min Act: -0.0003

Data Index: 519786 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6288. Min Act: -0.0002

Data Index: 79058 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6273. Min Act: -0.0003

Data Index: 29538 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6437. Min Act: -0.0002

Data Index: 1322994 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6437. Min Act: -0.0002

Data Index: 771249 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.9698. Min Range: -0.9698

Max Act: 0.6385. Min Act: -0.0002

Data Index: 672980 (C4 (Web Text))

Max Activating Token Index: 232