Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1802 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2546. Min Act: -0.0005

Data Index: 651131 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2047. Min Act: -0.0005

Data Index: 743054 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2085. Min Act: -0.0005

Data Index: 1097576 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1944. Min Act: -0.0005

Data Index: 130123 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2084. Min Act: -0.0005

Data Index: 589543 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1998. Min Act: -0.0005

Data Index: 878941 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2043. Min Act: -0.0005

Data Index: 576214 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.2020. Min Act: -0.0005

Data Index: 144591 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1929. Min Act: -0.0005

Data Index: 53964 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1847. Min Act: -0.0005

Data Index: 267400 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1978. Min Act: -0.0005

Data Index: 289245 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1822. Min Act: -0.0005

Data Index: 790301 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1805. Min Act: -0.0005

Data Index: 355650 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1749. Min Act: -0.0005

Data Index: 687578 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1785. Min Act: -0.0005

Data Index: 1199036 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1829. Min Act: -0.0005

Data Index: 355455 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1903. Min Act: -0.0005

Data Index: 1064597 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1835. Min Act: -0.0005

Data Index: 291506 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1828. Min Act: -0.0005

Data Index: 977249 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.2546. Min Range: -0.2546

Max Act: 0.1625. Min Act: -0.0005

Data Index: 1202841 (C4 (Web Text))

Max Activating Token Index: 731