Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3336 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.6875. Min Act: -0.0000

Data Index: 1204895 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9381. Min Act: -0.0000

Data Index: 405661 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.6562. Min Act: -0.0000

Data Index: 545373 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.8634. Min Act: -0.0000

Data Index: 914882 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.6740. Min Act: -0.0000

Data Index: 1114640 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 5.0357. Min Range: -5.0357

Max Act: 5.0357. Min Act: -0.0000

Data Index: 1166984 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.6341. Min Act: -0.0000

Data Index: 665207 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9706. Min Act: -0.0000

Data Index: 703120 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 5.0357. Min Range: -5.0357

Max Act: 5.0000. Min Act: -0.0000

Data Index: 24509 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.4132. Min Act: -0.0000

Data Index: 498011 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9725. Min Act: -0.0000

Data Index: 443647 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.7525. Min Act: -0.0000

Data Index: 905459 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.7101. Min Act: -0.0000

Data Index: 975234 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.4681. Min Act: -0.0000

Data Index: 1114137 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.6567. Min Act: -0.0000

Data Index: 443593 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.4950. Min Act: -0.0000

Data Index: 488826 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.4987. Min Act: -0.0000

Data Index: 35793 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.6635. Min Act: -0.0000

Data Index: 1125823 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.4750. Min Act: -0.0000

Data Index: 300476 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.4729. Min Act: -0.0000

Data Index: 1067461 (C4 (Web Text))

Max Activating Token Index: 51