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

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

Neuron 5330 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5524. Min Act: -0.0002

Data Index: 1614023 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4597. Min Act: -0.0002

Data Index: 1482822 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4409. Min Act: -0.0002

Data Index: 1445195 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4252. Min Act: -0.0002

Data Index: 1516370 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4180. Min Act: -0.0002

Data Index: 1381889 (Python Code)

Max Activating Token Index: 236

Text #5

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3991. Min Act: -0.0002

Data Index: 1398057 (Python Code)

Max Activating Token Index: 280

Text #6

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3846. Min Act: -0.0002

Data Index: 1453101 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3969. Min Act: -0.0002

Data Index: 1622505 (Python Code)

Max Activating Token Index: 479

Text #8

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3816. Min Act: -0.0002

Data Index: 1390334 (Python Code)

Max Activating Token Index: 646

Text #9

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3761. Min Act: -0.0002

Data Index: 1608067 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3735. Min Act: -0.0002

Data Index: 1363395 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3765. Min Act: -0.0002

Data Index: 1529160 (Python Code)

Max Activating Token Index: 712

Text #12

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3530. Min Act: -0.0002

Data Index: 1597696 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3550. Min Act: -0.0002

Data Index: 1511538 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3382. Min Act: -0.0002

Data Index: 1447730 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3487. Min Act: -0.0002

Data Index: 1434665 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3490. Min Act: -0.0002

Data Index: 1477343 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3561. Min Act: -0.0002

Data Index: 1371394 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3402. Min Act: -0.0002

Data Index: 1622710 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3257. Min Act: -0.0002

Data Index: 1538363 (Python Code)

Max Activating Token Index: 37