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

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

Neuron 4159 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: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1514573 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4097. Min Act: -0.0000

Data Index: 407738 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1570503 (Python Code)

Max Activating Token Index: 867

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3284. Min Act: -0.0000

Data Index: 613182 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1360244 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3085. Min Act: -0.0000

Data Index: 469298 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1462420 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1579688 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1651506 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1546426 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1499822 (Python Code)

Max Activating Token Index: 501

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1480828 (Python Code)

Max Activating Token Index: 216

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1628255 (Python Code)

Max Activating Token Index: 618

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3093. Min Act: -0.0000

Data Index: 593149 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2499. Min Act: -0.0000

Data Index: 452108 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1086523 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1458647 (Python Code)

Max Activating Token Index: 234

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1551827 (Python Code)

Max Activating Token Index: 262

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1411388 (Python Code)

Max Activating Token Index: 863

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.2355. Min Act: 0.0001

Data Index: 1077123 (C4 (Web Text))

Max Activating Token Index: 790