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

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

Neuron 3670 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.9715. Min Act: -0.0000

Data Index: 833546 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.0623. Min Act: -0.0000

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.8714. Min Act: -0.0000

Data Index: 1314546 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.3006. Min Act: -0.0000

Data Index: 875574 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.1186. Min Act: -0.0000

Data Index: 914069 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.0746. Min Act: -0.0000

Data Index: 895839 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.8472. Min Act: -0.0000

Data Index: 1165208 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.9821. Min Act: -0.0000

Data Index: 1337153 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.9957. Min Act: -0.0000

Data Index: 122033 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.8765. Min Act: -0.0000

Data Index: 98669 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.9950. Min Act: -0.0000

Data Index: 160114 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.1355. Min Act: -0.0000

Data Index: 603517 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.0084. Min Act: -0.0000

Data Index: 584211 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.1433. Min Act: -0.0000

Data Index: 569113 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.0012. Min Act: -0.0000

Data Index: 736577 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.1323. Min Act: -0.0000

Data Index: 108763 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.1361. Min Act: -0.0000

Data Index: 302101 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.0022. Min Act: -0.0001

Data Index: 681403 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 3.3006. Min Range: -3.3006

Max Act: 3.1485. Min Act: -0.0000

Data Index: 885737 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 3.3006. Min Range: -3.3006

Max Act: 2.8151. Min Act: -0.0000

Data Index: 451819 (C4 (Web Text))

Max Activating Token Index: 902