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

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

Neuron 4746 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: 1.0167. Min Range: -1.0167

Max Act: 0.9552. Min Act: -0.0000

Data Index: 59634 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0000

Data Index: 138929 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7656. Min Act: -0.0000

Data Index: 240547 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0019. Min Act: -0.0000

Data Index: 672707 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9715. Min Act: -0.0000

Data Index: 755579 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9331. Min Act: -0.0000

Data Index: 839072 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9030. Min Act: -0.0000

Data Index: 803911 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8926. Min Act: -0.0000

Data Index: 970959 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7826. Min Act: -0.0000

Data Index: 512624 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9475. Min Act: -0.0000

Data Index: 5902 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8916. Min Act: -0.0000

Data Index: 125522 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8823. Min Act: -0.0000

Data Index: 601589 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8078. Min Act: -0.0000

Data Index: 103265 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8441. Min Act: -0.0000

Data Index: 319542 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1210831 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8273. Min Act: -0.0000

Data Index: 123819 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8033. Min Act: -0.0000

Data Index: 221362 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1489332 (Python Code)

Max Activating Token Index: 413

Text #18

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1038774 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7640. Min Act: -0.0000

Data Index: 90803 (C4 (Web Text))

Max Activating Token Index: 950