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

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

Neuron 2563 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: 0.5617. Min Range: -0.5617

Max Act: 0.5617. Min Act: -0.0000

Data Index: 244437 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1260467 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4625. Min Act: -0.0000

Data Index: 27586 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1104070 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3935. Min Act: -0.0000

Data Index: 5772 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4296. Min Act: -0.0000

Data Index: 340537 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1277688 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1338424 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3763. Min Act: -0.0000

Data Index: 458719 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3955. Min Act: -0.0000

Data Index: 952030 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1290511 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3693. Min Act: -0.0000

Data Index: 832770 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3542. Min Act: -0.0000

Data Index: 232687 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3559. Min Act: -0.0000

Data Index: 644332 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3433. Min Act: -0.0000

Data Index: 867150 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3374. Min Act: -0.0000

Data Index: 539116 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3297. Min Act: -0.0000

Data Index: 394787 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3196. Min Act: -0.0000

Data Index: 970606 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3032. Min Act: -0.0000

Data Index: 438364 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3368. Min Act: -0.0000

Data Index: 827391 (C4 (Web Text))

Max Activating Token Index: 50