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

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

Neuron 4725 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.7860. Min Act: -0.0000

Data Index: 507363 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.7841. Min Act: -0.0000

Data Index: 712576 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6965. Min Act: -0.0000

Data Index: 761621 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.7014. Min Act: -0.0000

Data Index: 802209 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6718. Min Act: -0.0000

Data Index: 538114 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6407. Min Act: -0.0000

Data Index: 494441 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6748. Min Act: -0.0000

Data Index: 46388 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6562. Min Act: -0.0000

Data Index: 992175 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6619. Min Act: -0.0000

Data Index: 764735 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6420. Min Act: -0.0000

Data Index: 237793 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6261. Min Act: -0.0000

Data Index: 874981 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6233. Min Act: -0.0000

Data Index: 427669 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6394. Min Act: -0.0000

Data Index: 799695 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6117. Min Act: -0.0000

Data Index: 172484 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.5905. Min Act: -0.0000

Data Index: 149073 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1231998 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1177498 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.5981. Min Act: -0.0000

Data Index: 754634 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.5712. Min Act: -0.0000

Data Index: 925699 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.7860. Min Range: -0.7860

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1084884 (C4 (Web Text))

Max Activating Token Index: 922