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

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

Neuron 676 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: 3.6842. Min Range: -3.6842

Max Act: 3.6842. Min Act: -0.0000

Data Index: 957917 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 3.6842. Min Range: -3.6842

Max Act: 3.0390. Min Act: -0.0000

Data Index: 897898 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.9819. Min Act: -0.0000

Data Index: 11988 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.9522. Min Act: -0.0000

Data Index: 884567 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.8459. Min Act: -0.0000

Data Index: 407075 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.8668. Min Act: -0.0000

Data Index: 907428 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.9886. Min Act: -0.0000

Data Index: 66184 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.9507. Min Act: -0.0000

Data Index: 574896 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.7851. Min Act: -0.0000

Data Index: 1298561 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 3.6842. Min Range: -3.6842

Max Act: 3.0134. Min Act: -0.0000

Data Index: 1061778 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.8543. Min Act: -0.0000

Data Index: 739254 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.9673. Min Act: -0.0000

Data Index: 36593 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.6917. Min Act: -0.0000

Data Index: 912835 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.7904. Min Act: -0.0000

Data Index: 485072 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.8064. Min Act: -0.0000

Data Index: 1315159 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.6484. Min Act: -0.0000

Data Index: 322091 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.6234. Min Act: -0.0000

Data Index: 1003819 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.7594. Min Act: -0.0000

Data Index: 1079928 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.7541. Min Act: -0.0000

Data Index: 390859 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 3.6842. Min Range: -3.6842

Max Act: 2.8889. Min Act: -0.0000

Data Index: 848174 (C4 (Web Text))

Max Activating Token Index: 48