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

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

Neuron 530 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: 0.9898. Min Range: -0.9898

Max Act: 0.9898. Min Act: -0.0002

Data Index: 458991 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9554. Min Act: -0.0002

Data Index: 991856 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9316. Min Act: -0.0002

Data Index: 1034839 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9177. Min Act: -0.0002

Data Index: 843892 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9098. Min Act: -0.0002

Data Index: 320615 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9035. Min Act: -0.0002

Data Index: 1025154 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9159. Min Act: -0.0002

Data Index: 590415 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8938. Min Act: -0.0002

Data Index: 456249 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8898. Min Act: -0.0002

Data Index: 1154702 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8801. Min Act: -0.0002

Data Index: 903449 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9044. Min Act: -0.0002

Data Index: 281069 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.9027. Min Act: -0.0002

Data Index: 1188825 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8784. Min Act: -0.0002

Data Index: 510031 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8876. Min Act: -0.0002

Data Index: 64761 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8796. Min Act: -0.0002

Data Index: 399954 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8683. Min Act: -0.0002

Data Index: 1056741 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8692. Min Act: -0.0002

Data Index: 1270306 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8746. Min Act: -0.0002

Data Index: 141081 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8888. Min Act: -0.0002

Data Index: 510066 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.9898. Min Range: -0.9898

Max Act: 0.8753. Min Act: -0.0002

Data Index: 774856 (C4 (Web Text))

Max Activating Token Index: 661