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

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

Neuron 4352 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1164830 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5742. Min Act: -0.0000

Data Index: 43584 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4800. Min Act: -0.0000

Data Index: 174219 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4966. Min Act: -0.0000

Data Index: 771742 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4618. Min Act: -0.0000

Data Index: 800918 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4275. Min Act: -0.0000

Data Index: 636963 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5013. Min Act: -0.0000

Data Index: 228130 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4284. Min Act: -0.0000

Data Index: 203270 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1032747 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4245. Min Act: -0.0000

Data Index: 64059 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4295. Min Act: -0.0000

Data Index: 187543 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4103. Min Act: -0.0000

Data Index: 16427 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1297084 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1065544 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.3996. Min Act: -0.0000

Data Index: 87000 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4180. Min Act: -0.0000

Data Index: 815885 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.3577. Min Act: -0.0000

Data Index: 626739 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.3665. Min Act: -0.0000

Data Index: 387340 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.3925. Min Act: -0.0000

Data Index: 547954 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1005947 (C4 (Web Text))

Max Activating Token Index: 994