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

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

Neuron 3236 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6567. Min Range: -4.6567

Max Act: 4.6567. Min Act: -0.0000

Data Index: 1459942 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 4.6567. Min Range: -4.6567

Max Act: 3.7136. Min Act: -0.0000

Data Index: 1498076 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 4.6567. Min Range: -4.6567

Max Act: 3.5225. Min Act: -0.0000

Data Index: 1481815 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 4.6567. Min Range: -4.6567

Max Act: 3.4814. Min Act: -0.0000

Data Index: 1613231 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 4.6567. Min Range: -4.6567

Max Act: 3.2989. Min Act: -0.0000

Data Index: 1492897 (Python Code)

Max Activating Token Index: 649

Text #5

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.9524. Min Act: -0.0000

Data Index: 1539581 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 4.6567. Min Range: -4.6567

Max Act: 2.0104. Min Act: -0.0000

Data Index: 1551469 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1518872 (Python Code)

Max Activating Token Index: 424

Text #8

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1353818 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.6808. Min Act: -0.0000

Data Index: 425131 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.7851. Min Act: -0.0000

Data Index: 1392389 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 4.6567. Min Range: -4.6567

Max Act: 2.0024. Min Act: -0.0000

Data Index: 1640505 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.7846. Min Act: -0.0000

Data Index: 481767 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.7147. Min Act: -0.0000

Data Index: 567170 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.6017. Min Act: -0.0000

Data Index: 540609 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.7017. Min Act: -0.0000

Data Index: 1208368 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.6923. Min Act: -0.0000

Data Index: 463156 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.6985. Min Act: -0.0000

Data Index: 717934 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1179520 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 4.6567. Min Range: -4.6567

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1020435 (C4 (Web Text))

Max Activating Token Index: 611