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

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

Neuron 1725 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6845. Min Range: -2.6845

Max Act: 2.6845. Min Act: -0.0000

Data Index: 325163 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 2.6845. Min Range: -2.6845

Max Act: 2.1651. Min Act: -0.0000

Data Index: 746355 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 2.6845. Min Range: -2.6845

Max Act: 2.1104. Min Act: -0.0000

Data Index: 289427 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.9848. Min Act: -0.0000

Data Index: 1083647 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.9888. Min Act: -0.0000

Data Index: 608629 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 2.6845. Min Range: -2.6845

Max Act: 2.0326. Min Act: -0.0000

Data Index: 744927 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.8677. Min Act: -0.0000

Data Index: 1065978 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.7597. Min Act: -0.0000

Data Index: 1335600 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1313547 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1277334 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.5590. Min Act: -0.0000

Data Index: 103936 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.6178. Min Act: -0.0000

Data Index: 38407 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1195557 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1327972 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1537001 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1129012 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.4809. Min Act: -0.0000

Data Index: 1628012 (Python Code)

Max Activating Token Index: 546

Text #17

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.5371. Min Act: -0.0000

Data Index: 450795 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1464246 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 2.6845. Min Range: -2.6845

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1241657 (C4 (Web Text))

Max Activating Token Index: 679