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

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

Neuron 167 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0002

Data Index: 687285 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1026652 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0630. Min Act: -0.0002

Data Index: 671860 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0605. Min Act: -0.0002

Data Index: 399901 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0665. Min Act: -0.0002

Data Index: 504625 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1200491 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0553. Min Act: -0.0002

Data Index: 344583 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1154743 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0576. Min Act: -0.0002

Data Index: 871931 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0575. Min Act: -0.0002

Data Index: 496528 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0587. Min Act: -0.0002

Data Index: 416319 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0587. Min Act: -0.0002

Data Index: 410905 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0561. Min Act: -0.0002

Data Index: 291000 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0585. Min Act: -0.0002

Data Index: 613216 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1187329 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0536. Min Act: -0.0002

Data Index: 33779 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0537. Min Act: -0.0002

Data Index: 619268 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0572. Min Act: -0.0002

Data Index: 217294 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0517. Min Act: -0.0002

Data Index: 623503 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1125348 (C4 (Web Text))

Max Activating Token Index: 520