Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1169171 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1377280 (Python Code)

Max Activating Token Index: 782

Text #2

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1370041 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1424674 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3592. Min Act: -0.0000

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1580415 (Python Code)

Max Activating Token Index: 639

Text #6

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3488. Min Act: -0.0000

Data Index: 932393 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3037. Min Act: -0.0000

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1573941 (Python Code)

Max Activating Token Index: 391

Text #9

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1512346 (Python Code)

Max Activating Token Index: 915

Text #10

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3221. Min Act: -0.0000

Data Index: 88162 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1428374 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1381053 (Python Code)

Max Activating Token Index: 813

Text #13

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2831. Min Act: -0.0000

Data Index: 112788 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1385426 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2724. Min Act: -0.0000

Data Index: 445173 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3017. Min Act: -0.0000

Data Index: 353858 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2631. Min Act: -0.0000

Data Index: 539561 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1584584 (Python Code)

Max Activating Token Index: 218

Text #19

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1103258 (C4 (Web Text))

Max Activating Token Index: 231