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

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

Neuron 3876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1165256 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.6202. Min Act: -0.0001

Data Index: 647349 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.6277. Min Act: -0.0001

Data Index: 898617 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5362. Min Act: -0.0001

Data Index: 212327 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5337. Min Act: -0.0000

Data Index: 890471 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1006627 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1342503 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1049784 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1200871 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5633. Min Act: -0.0001

Data Index: 526958 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5210. Min Act: -0.0000

Data Index: 336049 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5155. Min Act: -0.0001

Data Index: 385180 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4949. Min Act: -0.0001

Data Index: 551654 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.5222. Min Act: -0.0001

Data Index: 167380 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4770. Min Act: -0.0001

Data Index: 620047 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4699. Min Act: -0.0001

Data Index: 942846 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4932. Min Act: -0.0001

Data Index: 212440 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4982. Min Act: -0.0001

Data Index: 377571 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1200744 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.7354. Min Range: -0.7354

Max Act: 0.4955. Min Act: -0.0001

Data Index: 363453 (C4 (Web Text))

Max Activating Token Index: 454