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

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

Neuron 4685 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: 4.7841. Min Range: -4.7841

Max Act: 4.7841. Min Act: -0.0000

Data Index: 570283 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 4.7841. Min Range: -4.7841

Max Act: 4.3071. Min Act: -0.0000

Data Index: 493629 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 4.7841. Min Range: -4.7841

Max Act: 4.2015. Min Act: -0.0000

Data Index: 1211575 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 4.7841. Min Range: -4.7841

Max Act: 4.0784. Min Act: -0.0000

Data Index: 230468 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.9840. Min Act: -0.0000

Data Index: 1343220 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.9736. Min Act: -0.0000

Data Index: 710411 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.9227. Min Act: -0.0000

Data Index: 968888 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.8626. Min Act: -0.0000

Data Index: 882561 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.8832. Min Act: -0.0000

Data Index: 711792 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.8556. Min Act: -0.0000

Data Index: 456312 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 4.7841. Min Range: -4.7841

Max Act: 4.0130. Min Act: -0.0000

Data Index: 812300 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.9790. Min Act: -0.0000

Data Index: 80381 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.6311. Min Act: -0.0000

Data Index: 568871 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.6142. Min Act: -0.0000

Data Index: 122699 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.5892. Min Act: -0.0000

Data Index: 1237994 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.7330. Min Act: -0.0000

Data Index: 121103 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.7265. Min Act: -0.0000

Data Index: 524126 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.7209. Min Act: -0.0000

Data Index: 443346 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.7055. Min Act: -0.0000

Data Index: 528869 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 4.7841. Min Range: -4.7841

Max Act: 3.4907. Min Act: -0.0000

Data Index: 1250638 (C4 (Web Text))

Max Activating Token Index: 179