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

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

Neuron 483 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.8154. Min Act: -0.0000

Data Index: 797530 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.8173. Min Act: -0.0000

Data Index: 498704 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.7135. Min Act: -0.0000

Data Index: 434270 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.6791. Min Act: -0.0000

Data Index: 740726 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.7280. Min Act: -0.0000

Data Index: 360047 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.7201. Min Act: -0.0000

Data Index: 839278 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5856. Min Act: -0.0000

Data Index: 698538 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1152641 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5722. Min Act: -0.0000

Data Index: 706198 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5795. Min Act: -0.0000

Data Index: 13817 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.6012. Min Act: -0.0000

Data Index: 280 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1202255 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5105. Min Act: -0.0000

Data Index: 901173 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5361. Min Act: -0.0000

Data Index: 892441 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5392. Min Act: -0.0000

Data Index: 346441 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5398. Min Act: -0.0000

Data Index: 386496 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5440. Min Act: -0.0000

Data Index: 423797 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5338. Min Act: -0.0000

Data Index: 260284 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.4917. Min Act: -0.0000

Data Index: 235069 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.4953. Min Act: -0.0000

Data Index: 506718 (C4 (Web Text))

Max Activating Token Index: 159