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

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

Neuron 953 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.3655. Min Act: -0.0000

Data Index: 534396 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.3326. Min Act: -0.0000

Data Index: 926342 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1236473 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.2750. Min Act: -0.0000

Data Index: 190289 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1222226 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1021539 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1794. Min Act: -0.0000

Data Index: 77391 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1189482 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.2108. Min Act: -0.0000

Data Index: 849434 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0915. Min Act: -0.0000

Data Index: 722540 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0090. Min Act: -0.0000

Data Index: 665518 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1078. Min Act: -0.0000

Data Index: 836979 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0244. Min Act: -0.0000

Data Index: 422580 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0935. Min Act: -0.0000

Data Index: 771675 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0480. Min Act: -0.0000

Data Index: 802267 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0143. Min Act: -0.0000

Data Index: 646112 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0420. Min Act: -0.0000

Data Index: 215986 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9970. Min Act: -0.0000

Data Index: 655831 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9584. Min Act: -0.0000

Data Index: 638730 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1193755 (C4 (Web Text))

Max Activating Token Index: 640