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

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

Neuron 1223 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: 0.9059. Min Range: -0.9059

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1190203 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1555418 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1568627 (Python Code)

Max Activating Token Index: 344

Text #3

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8315. Min Act: 0.0000

Data Index: 1578264 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1525452 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6691. Min Act: -0.0000

Data Index: 794699 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7275. Min Act: -0.0000

Data Index: 16105 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1577317 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6615. Min Act: -0.0000

Data Index: 619399 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6550. Min Act: -0.0000

Data Index: 517167 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5942. Min Act: -0.0000

Data Index: 702408 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1628171 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6812. Min Act: -0.0000

Data Index: 101246 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1368514 (Python Code)

Max Activating Token Index: 549

Text #14

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6822. Min Act: 0.0000

Data Index: 15909 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6513. Min Act: -0.0000

Data Index: 759888 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6217. Min Act: -0.0000

Data Index: 74929 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5839. Min Act: -0.0000

Data Index: 485728 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5973. Min Act: -0.0000

Data Index: 519273 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1470012 (Python Code)

Max Activating Token Index: 255