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

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

Neuron 1060 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: 0.8721. Min Range: -0.8721

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1136190 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1123207 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7889. Min Act: -0.0000

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7902. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7631. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1354143 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6715. Min Act: -0.0000

Data Index: 924975 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6278. Min Act: -0.0000

Data Index: 693961 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6293. Min Act: -0.0000

Data Index: 924379 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6237. Min Act: -0.0000

Data Index: 614262 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.5909. Min Act: -0.0000

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6297. Min Act: -0.0000

Data Index: 690450 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.5857. Min Act: -0.0000

Data Index: 302336 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1603664 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6537. Min Act: -0.0000

Data Index: 59273 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.5796. Min Act: -0.0000

Data Index: 629269 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6240. Min Act: -0.0000

Data Index: 415636 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.5985. Min Act: -0.0000

Data Index: 166639 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.5583. Min Act: -0.0000

Data Index: 986319 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1198036 (C4 (Web Text))

Max Activating Token Index: 206