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

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

Neuron 2454 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2358. Min Act: -0.0000

Data Index: 16120 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1063326 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2258. Min Act: -0.0000

Data Index: 987302 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2067. Min Act: -0.0000

Data Index: 784541 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2116. Min Act: -0.0000

Data Index: 4713 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2099. Min Act: -0.0000

Data Index: 279121 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2004. Min Act: -0.0000

Data Index: 686928 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1998. Min Act: -0.0000

Data Index: 543906 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2050. Min Act: -0.0000

Data Index: 409639 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1981. Min Act: -0.0000

Data Index: 74348 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2051. Min Act: -0.0000

Data Index: 547801 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1161684 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1352785 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1854. Min Act: -0.0000

Data Index: 790669 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1985. Min Act: -0.0000

Data Index: 898415 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1902. Min Act: -0.0000

Data Index: 72021 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1087442 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1177812 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1954. Min Act: -0.0000

Data Index: 666149 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1341898 (C4 (Web Text))

Max Activating Token Index: 105