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

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

Neuron 94 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.6720. Min Act: -0.0000

Data Index: 1241560 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.5652. Min Act: -0.0000

Data Index: 689652 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.6327. Min Act: -0.0000

Data Index: 803052 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.6154. Min Act: -0.0000

Data Index: 377859 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1054920 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.5105. Min Act: -0.0001

Data Index: 1264015 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.2771. Min Act: -0.0001

Data Index: 165338 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.3669. Min Act: -0.0000

Data Index: 1228294 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1318546 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.4200. Min Act: -0.0000

Data Index: 209205 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.3508. Min Act: -0.0000

Data Index: 627826 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.5428. Min Act: -0.0000

Data Index: 1245952 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.2717. Min Act: -0.0000

Data Index: 272300 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.3513. Min Act: -0.0000

Data Index: 766135 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.3918. Min Act: -0.0000

Data Index: 585282 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.3362. Min Act: -0.0000

Data Index: 355474 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.3208. Min Act: -0.0000

Data Index: 932954 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.3990. Min Act: -0.0000

Data Index: 763018 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.4472. Min Act: -0.0000

Data Index: 634747 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.6720. Min Range: -1.6720

Max Act: 1.2691. Min Act: -0.0000

Data Index: 955499 (C4 (Web Text))

Max Activating Token Index: 654