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

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

Neuron 2821 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0868. Min Range: -1.0868

Max Act: 1.0868. Min Act: -0.0002

Data Index: 171276 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.0868. Min Range: -1.0868

Max Act: 1.0605. Min Act: -0.0002

Data Index: 442305 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.0868. Min Range: -1.0868

Max Act: 1.0405. Min Act: -0.0002

Data Index: 1311100 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9847. Min Act: -0.0002

Data Index: 744205 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9673. Min Act: -0.0002

Data Index: 703164 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9354. Min Act: -0.0002

Data Index: 595914 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9215. Min Act: -0.0002

Data Index: 389376 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9190. Min Act: -0.0002

Data Index: 548838 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9339. Min Act: -0.0002

Data Index: 550689 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1215640 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9176. Min Act: -0.0002

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9314. Min Act: -0.0002

Data Index: 672314 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8896. Min Act: -0.0002

Data Index: 101433 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8864. Min Act: -0.0002

Data Index: 1076358 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8709. Min Act: -0.0002

Data Index: 293287 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8604. Min Act: -0.0002

Data Index: 487767 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8777. Min Act: -0.0002

Data Index: 979473 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8853. Min Act: -0.0002

Data Index: 598376 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8867. Min Act: -0.0002

Data Index: 561470 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8785. Min Act: -0.0002

Data Index: 424976 (C4 (Web Text))

Max Activating Token Index: 568