Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4875 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8736. Min Act: -0.0000

Data Index: 105489 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7713. Min Act: -0.0000

Data Index: 224819 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7878. Min Act: -0.0000

Data Index: 432863 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7999. Min Act: -0.0000

Data Index: 245341 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7564. Min Act: -0.0000

Data Index: 619202 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7490. Min Act: -0.0000

Data Index: 908806 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7567. Min Act: 0.0000

Data Index: 112909 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7021. Min Act: 0.0000

Data Index: 1185965 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6853. Min Act: -0.0000

Data Index: 644105 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6610. Min Act: -0.0000

Data Index: 335555 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6777. Min Act: 0.0000

Data Index: 1244305 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1307815 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6623. Min Act: 0.0000

Data Index: 1289344 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6219. Min Act: -0.0000

Data Index: 517873 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5394. Min Act: -0.0000

Data Index: 598357 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1291867 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6210. Min Act: -0.0000

Data Index: 364714 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1311964 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6157. Min Act: -0.0000

Data Index: 90105 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5934. Min Act: -0.0000

Data Index: 626697 (C4 (Web Text))

Max Activating Token Index: 115