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

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

Neuron 4254 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1202884 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8927. Min Act: -0.0000

Data Index: 941168 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8595. Min Act: -0.0000

Data Index: 806653 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7683. Min Act: -0.0000

Data Index: 852536 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1199283 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7599. Min Act: -0.0000

Data Index: 983896 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7695. Min Act: -0.0000

Data Index: 515748 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7230. Min Act: -0.0000

Data Index: 597865 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6925. Min Act: -0.0000

Data Index: 391066 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1223469 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7137. Min Act: -0.0000

Data Index: 954453 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6904. Min Act: -0.0000

Data Index: 357177 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7358. Min Act: -0.0000

Data Index: 252747 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6628. Min Act: -0.0000

Data Index: 692028 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6828. Min Act: -0.0000

Data Index: 624092 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6492. Min Act: -0.0000

Data Index: 953091 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1128425 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6925. Min Act: -0.0000

Data Index: 69690 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6557. Min Act: -0.0000

Data Index: 950821 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1173129 (C4 (Web Text))

Max Activating Token Index: 482