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

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

Neuron 3768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0812. Min Range: -1.0812

Max Act: 1.0812. Min Act: -0.0000

Data Index: 868392 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.0812. Min Range: -1.0812

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1314923 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9146. Min Act: -0.0000

Data Index: 672980 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9530. Min Act: -0.0000

Data Index: 574736 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9358. Min Act: -0.0000

Data Index: 840732 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9149. Min Act: -0.0000

Data Index: 725483 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9179. Min Act: -0.0000

Data Index: 819614 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9675. Min Act: -0.0000

Data Index: 835499 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8863. Min Act: -0.0000

Data Index: 306373 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8471. Min Act: -0.0000

Data Index: 170264 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9208. Min Act: -0.0000

Data Index: 462429 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.9078. Min Act: -0.0000

Data Index: 661769 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1073619 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8542. Min Act: -0.0000

Data Index: 370844 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8098. Min Act: -0.0000

Data Index: 43021 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1380885 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8352. Min Act: -0.0000

Data Index: 651516 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8529. Min Act: -0.0000

Data Index: 966644 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8529. Min Act: -0.0000

Data Index: 332297 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.0812. Min Range: -1.0812

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1307283 (C4 (Web Text))

Max Activating Token Index: 174