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

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

Neuron 3321 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: 7.2803. Min Range: -7.2803

Max Act: 7.0308. Min Act: -0.0000

Data Index: 820148 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 7.2803. Min Range: -7.2803

Max Act: 7.1811. Min Act: -0.0000

Data Index: 77343 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 7.2803. Min Range: -7.2803

Max Act: 7.1664. Min Act: -0.0000

Data Index: 813582 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.8962. Min Act: -0.0000

Data Index: 771055 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 7.2803. Min Range: -7.2803

Max Act: 7.2464. Min Act: -0.0000

Data Index: 486132 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 7.2803. Min Range: -7.2803

Max Act: 7.2803. Min Act: -0.0000

Data Index: 691101 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 7.2803. Min Range: -7.2803

Max Act: 7.0607. Min Act: -0.0000

Data Index: 1080090 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.8525. Min Act: -0.0000

Data Index: 140463 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 7.2803. Min Range: -7.2803

Max Act: 7.0169. Min Act: -0.0000

Data Index: 170883 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.7821. Min Act: -0.0000

Data Index: 248849 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.7856. Min Act: -0.0000

Data Index: 466494 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.7726. Min Act: -0.0000

Data Index: 427886 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.8721. Min Act: -0.0000

Data Index: 733089 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.7028. Min Act: -0.0000

Data Index: 11698 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.6935. Min Act: -0.0000

Data Index: 890949 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 7.2803. Min Range: -7.2803

Max Act: 7.0329. Min Act: -0.0000

Data Index: 868273 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.8281. Min Act: -0.0000

Data Index: 72851 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.2419. Min Act: -0.0000

Data Index: 1321967 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.5640. Min Act: -0.0000

Data Index: 523819 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 7.2803. Min Range: -7.2803

Max Act: 6.8775. Min Act: -0.0000

Data Index: 1090513 (C4 (Web Text))

Max Activating Token Index: 161