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

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

Neuron 2472 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.9060. Min Act: -0.0000

Data Index: 702256 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.5369. Min Act: -0.0000

Data Index: 873201 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.4957. Min Act: -0.0000

Data Index: 1250428 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.3281. Min Act: -0.0000

Data Index: 376959 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.1561. Min Act: -0.0000

Data Index: 143130 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.0447. Min Act: -0.0000

Data Index: 976634 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.1694. Min Act: -0.0000

Data Index: 1103467 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.0032. Min Act: -0.0000

Data Index: 1195450 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.9788. Min Act: -0.0000

Data Index: 1169686 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.9666. Min Act: -0.0000

Data Index: 144780 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.0208. Min Act: -0.0000

Data Index: 1114229 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.9852. Min Act: -0.0000

Data Index: 52504 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.9631. Min Act: -0.0000

Data Index: 361446 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.6851. Min Act: -0.0000

Data Index: 176694 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.5779. Min Act: -0.0000

Data Index: 718460 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.5172. Min Act: -0.0000

Data Index: 862112 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.5302. Min Act: -0.0000

Data Index: 1059466 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.4479. Min Act: -0.0000

Data Index: 1337343 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.3020. Min Act: -0.0000

Data Index: 651922 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 3.9060. Min Range: -3.9060

Max Act: 2.3289. Min Act: -0.0000

Data Index: 1224847 (C4 (Web Text))

Max Activating Token Index: 296