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

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

Neuron 4476 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1358184 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.9624. Min Act: -0.0000

Data Index: 214808 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8828. Min Act: -0.0000

Data Index: 942707 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1247241 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8947. Min Act: -0.0000

Data Index: 121878 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8294. Min Act: -0.0000

Data Index: 426478 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8772. Min Act: -0.0000

Data Index: 861685 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7692. Min Act: -0.0000

Data Index: 489416 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8072. Min Act: -0.0000

Data Index: 796276 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7491. Min Act: -0.0000

Data Index: 955886 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7055. Min Act: -0.0000

Data Index: 146298 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1181211 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6771. Min Act: -0.0000

Data Index: 442527 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7275. Min Act: -0.0000

Data Index: 74196 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7249. Min Act: -0.0000

Data Index: 145240 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6524. Min Act: 0.0000

Data Index: 229624 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6448. Min Act: -0.0000

Data Index: 215769 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6674. Min Act: -0.0000

Data Index: 23613 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6434. Min Act: -0.0000

Data Index: 668282 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1102243 (C4 (Web Text))

Max Activating Token Index: 626