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

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

Neuron 4879 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1337557 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3678. Min Act: -0.0000

Data Index: 697351 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3384. Min Act: -0.0000

Data Index: 649355 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2981. Min Act: -0.0000

Data Index: 654760 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3148. Min Act: -0.0000

Data Index: 314636 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1192040 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3151. Min Act: -0.0000

Data Index: 291528 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2952. Min Act: -0.0000

Data Index: 999496 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2898. Min Act: -0.0000

Data Index: 158370 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2860. Min Act: -0.0000

Data Index: 583959 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2947. Min Act: -0.0000

Data Index: 378476 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2929. Min Act: -0.0000

Data Index: 773118 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2825. Min Act: -0.0000

Data Index: 403299 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2863. Min Act: -0.0000

Data Index: 4106 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1085010 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1046738 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2701. Min Act: -0.0000

Data Index: 38076 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2687. Min Act: -0.0000

Data Index: 826458 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2755. Min Act: 0.0000

Data Index: 898369 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2718. Min Act: -0.0000

Data Index: 951830 (C4 (Web Text))

Max Activating Token Index: 183