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

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

Neuron 685 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: 0.4103. Min Range: -0.4103

Max Act: 0.4103. Min Act: -0.0002

Data Index: 88666 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3834. Min Act: -0.0002

Data Index: 1137666 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3604. Min Act: -0.0002

Data Index: 1351776 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3883. Min Act: -0.0002

Data Index: 645254 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3496. Min Act: -0.0002

Data Index: 256035 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3420. Min Act: -0.0002

Data Index: 261908 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3191. Min Act: -0.0002

Data Index: 776226 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3196. Min Act: -0.0002

Data Index: 308712 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3089. Min Act: -0.0002

Data Index: 681369 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2951. Min Act: -0.0002

Data Index: 1270002 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3012. Min Act: -0.0002

Data Index: 586123 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3026. Min Act: -0.0002

Data Index: 1121500 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2832. Min Act: -0.0002

Data Index: 331916 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2823. Min Act: -0.0002

Data Index: 232762 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2810. Min Act: -0.0002

Data Index: 714836 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2906. Min Act: -0.0002

Data Index: 862568 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3024. Min Act: -0.0002

Data Index: 29599 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2923. Min Act: -0.0002

Data Index: 649211 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2759. Min Act: -0.0002

Data Index: 225572 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2622. Min Act: -0.0002

Data Index: 1068606 (C4 (Web Text))

Max Activating Token Index: 629