Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 963 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0003

Data Index: 142941 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1137. Min Act: -0.0003

Data Index: 474080 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1106. Min Act: -0.0003

Data Index: 368004 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1115. Min Act: -0.0004

Data Index: 932169 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1061. Min Act: -0.0003

Data Index: 316062 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1023. Min Act: -0.0003

Data Index: 1109141 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1033. Min Act: -0.0003

Data Index: 878456 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1002. Min Act: -0.0003

Data Index: 789430 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1044. Min Act: -0.0003

Data Index: 323373 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0997. Min Act: -0.0003

Data Index: 498731 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0995. Min Act: -0.0003

Data Index: 846271 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1003. Min Act: -0.0003

Data Index: 1067644 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0964. Min Act: -0.0003

Data Index: 548877 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0984. Min Act: -0.0003

Data Index: 340722 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0971. Min Act: -0.0003

Data Index: 432146 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0973. Min Act: -0.0003

Data Index: 58768 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0987. Min Act: -0.0003

Data Index: 799355 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0986. Min Act: -0.0004

Data Index: 263332 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0966. Min Act: -0.0003

Data Index: 750561 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0968. Min Act: -0.0003

Data Index: 103198 (C4 (Web Text))

Max Activating Token Index: 814