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

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

Neuron 4531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6973. Min Range: -6.6973

Max Act: 6.6973. Min Act: -0.0000

Data Index: 935559 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 6.6973. Min Range: -6.6973

Max Act: 4.3054. Min Act: -0.0000

Data Index: 1177054 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 6.6973. Min Range: -6.6973

Max Act: 3.6566. Min Act: -0.0000

Data Index: 1256617 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 6.6973. Min Range: -6.6973

Max Act: 3.7071. Min Act: -0.0000

Data Index: 792761 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 6.6973. Min Range: -6.6973

Max Act: 3.6654. Min Act: -0.0000

Data Index: 142370 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 6.6973. Min Range: -6.6973

Max Act: 3.2852. Min Act: -0.0000

Data Index: 1123368 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 6.6973. Min Range: -6.6973

Max Act: 3.1948. Min Act: -0.0000

Data Index: 822160 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 6.6973. Min Range: -6.6973

Max Act: 3.0215. Min Act: -0.0000

Data Index: 82782 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 6.6973. Min Range: -6.6973

Max Act: 3.0771. Min Act: -0.0000

Data Index: 986179 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.8518. Min Act: -0.0000

Data Index: 945342 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.8123. Min Act: -0.0000

Data Index: 950358 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.6924. Min Act: -0.0000

Data Index: 26121 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.7835. Min Act: -0.0000

Data Index: 1061317 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.4260. Min Act: -0.0000

Data Index: 204523 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.6773. Min Act: -0.0000

Data Index: 248080 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.6823. Min Act: -0.0000

Data Index: 1338363 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.9327. Min Act: -0.0000

Data Index: 1131784 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.6281. Min Act: -0.0000

Data Index: 820543 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.6127. Min Act: -0.0000

Data Index: 980838 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 6.6973. Min Range: -6.6973

Max Act: 2.6072. Min Act: -0.0000

Data Index: 154729 (C4 (Web Text))

Max Activating Token Index: 511