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

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

Neuron 5022 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: 1.7112. Min Range: -1.7112

Max Act: 1.6080. Min Act: -0.0002

Data Index: 760072 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.5313. Min Act: -0.0002

Data Index: 748414 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6648. Min Act: -0.0002

Data Index: 526669 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6171. Min Act: -0.0002

Data Index: 1272790 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.3511. Min Act: -0.0002

Data Index: 976592 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.5201. Min Act: -0.0002

Data Index: 1093586 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.5090. Min Act: -0.0002

Data Index: 496778 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.7112. Min Act: -0.0002

Data Index: 1181527 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6184. Min Act: -0.0002

Data Index: 531842 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.3980. Min Act: -0.0002

Data Index: 431748 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.5838. Min Act: -0.0002

Data Index: 868397 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.4870. Min Act: -0.0002

Data Index: 280930 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.4596. Min Act: -0.0002

Data Index: 1036669 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.5776. Min Act: -0.0002

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6176. Min Act: -0.0002

Data Index: 934535 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.4532. Min Act: -0.0002

Data Index: 512888 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6923. Min Act: -0.0002

Data Index: 7467 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.6065. Min Act: -0.0002

Data Index: 163110 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.4310. Min Act: -0.0002

Data Index: 584142 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.7112. Min Range: -1.7112

Max Act: 1.5500. Min Act: -0.0002

Data Index: 44998 (C4 (Web Text))

Max Activating Token Index: 402