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

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

Neuron 3330 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.7428. Min Act: -0.0001

Data Index: 433337 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.4563. Min Act: -0.0001

Data Index: 621049 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5036. Min Act: -0.0001

Data Index: 1240719 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5941. Min Act: -0.0001

Data Index: 1211586 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5190. Min Act: -0.0001

Data Index: 529618 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5555. Min Act: -0.0001

Data Index: 402149 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.6339. Min Act: -0.0001

Data Index: 291689 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5926. Min Act: -0.0001

Data Index: 797708 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5887. Min Act: -0.0001

Data Index: 1269812 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.4291. Min Act: -0.0001

Data Index: 691499 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.4712. Min Act: -0.0001

Data Index: 554877 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5098. Min Act: -0.0001

Data Index: 691833 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.3712. Min Act: -0.0001

Data Index: 917439 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.4984. Min Act: -0.0001

Data Index: 39350 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.4830. Min Act: -0.0001

Data Index: 983303 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5695. Min Act: -0.0001

Data Index: 407493 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.4738. Min Act: -0.0001

Data Index: 229701 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5613. Min Act: -0.0001

Data Index: 1129001 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.3050. Min Act: -0.0001

Data Index: 355132 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.7428. Min Range: -1.7428

Max Act: 1.5017. Min Act: -0.0001

Data Index: 215632 (C4 (Web Text))

Max Activating Token Index: 158