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

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

Neuron 3712 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.6375. Min Act: -0.0000

Data Index: 159998 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1358746 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5315. Min Act: -0.0000

Data Index: 413684 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4918. Min Act: -0.0000

Data Index: 143903 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4449. Min Act: -0.0000

Data Index: 432577 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4972. Min Act: -0.0000

Data Index: 701436 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5056. Min Act: -0.0000

Data Index: 58664 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4035. Min Act: -0.0000

Data Index: 771025 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1209927 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4563. Min Act: -0.0000

Data Index: 806615 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4250. Min Act: -0.0000

Data Index: 84525 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4396. Min Act: -0.0000

Data Index: 64353 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4016. Min Act: -0.0000

Data Index: 253169 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4195. Min Act: -0.0000

Data Index: 640231 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1136659 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4229. Min Act: -0.0000

Data Index: 275415 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4229. Min Act: -0.0000

Data Index: 574159 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4146. Min Act: -0.0000

Data Index: 433950 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3790. Min Act: -0.0000

Data Index: 985913 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4002. Min Act: -0.0000

Data Index: 943893 (C4 (Web Text))

Max Activating Token Index: 1010