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

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

Neuron 1568 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: 4.0829. Min Range: -4.0829

Max Act: 4.0829. Min Act: -0.0000

Data Index: 1242628 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 4.0829. Min Range: -4.0829

Max Act: 3.9329. Min Act: -0.0000

Data Index: 483139 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 4.0829. Min Range: -4.0829

Max Act: 3.6518. Min Act: -0.0000

Data Index: 640966 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 4.0829. Min Range: -4.0829

Max Act: 3.2958. Min Act: -0.0000

Data Index: 1024983 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.9175. Min Act: -0.0000

Data Index: 956440 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.7662. Min Act: -0.0000

Data Index: 837448 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.5841. Min Act: -0.0000

Data Index: 1006283 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.6915. Min Act: -0.0000

Data Index: 56798 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.5272. Min Act: -0.0000

Data Index: 469627 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.2328. Min Act: -0.0000

Data Index: 883313 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.1878. Min Act: -0.0000

Data Index: 932743 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.3066. Min Act: -0.0000

Data Index: 561696 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.0632. Min Act: -0.0000

Data Index: 987842 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.2701. Min Act: -0.0000

Data Index: 1086847 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.1488. Min Act: -0.0000

Data Index: 425863 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 4.0829. Min Range: -4.0829

Max Act: 2.0006. Min Act: -0.0000

Data Index: 277187 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 4.0829. Min Range: -4.0829

Max Act: 1.8813. Min Act: -0.0000

Data Index: 543964 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 4.0829. Min Range: -4.0829

Max Act: 1.8754. Min Act: -0.0000

Data Index: 558015 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 4.0829. Min Range: -4.0829

Max Act: 1.8829. Min Act: -0.0000

Data Index: 1309079 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 4.0829. Min Range: -4.0829

Max Act: 1.8426. Min Act: -0.0000

Data Index: 801530 (C4 (Web Text))

Max Activating Token Index: 937