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

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

Neuron 3893 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.6473. Min Act: -0.0000

Data Index: 1562359 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.4490. Min Act: -0.0000

Data Index: 1042142 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.4506. Min Act: -0.0000

Data Index: 487002 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.6059. Min Act: -0.0000

Data Index: 1610822 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1456955 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1586551 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.2765. Min Act: -0.0000

Data Index: 1429902 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1638198 (Python Code)

Max Activating Token Index: 874

Text #8

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.2337. Min Act: -0.0000

Data Index: 1527341 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.2994. Min Act: -0.0000

Data Index: 255612 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1412. Min Act: -0.0000

Data Index: 1265798 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1358395 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1191178 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1413753 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1183. Min Act: -0.0000

Data Index: 243015 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1556298 (Python Code)

Max Activating Token Index: 110

Text #16

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1460834 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1621645 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1644740 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 1.6473. Min Range: -1.6473

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1427191 (Python Code)

Max Activating Token Index: 396