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

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

Neuron 3410 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: 2.0440. Min Range: -2.0440

Max Act: 2.0440. Min Act: -0.0002

Data Index: 1276311 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.9207. Min Act: -0.0002

Data Index: 1203484 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.9165. Min Act: -0.0002

Data Index: 787651 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.9589. Min Act: -0.0002

Data Index: 768333 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.9811. Min Act: -0.0002

Data Index: 1053263 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8895. Min Act: -0.0002

Data Index: 1342423 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8333. Min Act: -0.0002

Data Index: 567803 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.9154. Min Act: -0.0002

Data Index: 30122 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8962. Min Act: -0.0002

Data Index: 654960 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8173. Min Act: -0.0002

Data Index: 311872 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8418. Min Act: -0.0002

Data Index: 418094 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8741. Min Act: -0.0002

Data Index: 169596 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8795. Min Act: -0.0002

Data Index: 700777 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8867. Min Act: -0.0002

Data Index: 197791 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8533. Min Act: -0.0002

Data Index: 1208926 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.7494. Min Act: -0.0002

Data Index: 1345046 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8877. Min Act: -0.0002

Data Index: 833903 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.8445. Min Act: -0.0002

Data Index: 872014 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.7729. Min Act: -0.0002

Data Index: 990963 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.7843. Min Act: -0.0002

Data Index: 834646 (C4 (Web Text))

Max Activating Token Index: 38