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

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

Neuron 3072 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1031. Min Act: -0.0000

Data Index: 225441 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0923. Min Act: -0.0000

Data Index: 711101 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0883. Min Act: 0.0000

Data Index: 1098668 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0804. Min Act: -0.0000

Data Index: 756077 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1208677 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0779. Min Act: -0.0000

Data Index: 724840 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0768. Min Act: 0.0001

Data Index: 1342172 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0713. Min Act: -0.0000

Data Index: 664981 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1243486 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0759. Min Act: -0.0000

Data Index: 109791 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0695. Min Act: -0.0000

Data Index: 44886 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0728. Min Act: -0.0000

Data Index: 47037 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0669. Min Act: -0.0000

Data Index: 805577 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0678. Min Act: -0.0000

Data Index: 519614 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0716. Min Act: -0.0000

Data Index: 223452 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0714. Min Act: -0.0000

Data Index: 347978 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0664. Min Act: -0.0000

Data Index: 447971 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0702. Min Act: 0.0001

Data Index: 1037645 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0650. Min Act: -0.0000

Data Index: 239500 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0660. Min Act: -0.0000

Data Index: 380914 (C4 (Web Text))

Max Activating Token Index: 679