Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1419874 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1573568 (Python Code)

Max Activating Token Index: 446

Text #2

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1533228 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1487564 (Python Code)

Max Activating Token Index: 472

Text #4

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2056. Min Act: -0.0000

Data Index: 728512 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1885. Min Act: -0.0000

Data Index: 881458 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1945. Min Act: -0.0001

Data Index: 38921 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1487382 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1556563 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2070. Min Act: -0.0001

Data Index: 1438156 (Python Code)

Max Activating Token Index: 799

Text #10

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1493322 (Python Code)

Max Activating Token Index: 732

Text #11

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1540716 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1628052 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1646662 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1479762 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1838. Min Act: -0.0000

Data Index: 888786 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1471170 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1386072 (Python Code)

Max Activating Token Index: 549

Text #18

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1410729 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1519215 (Python Code)

Max Activating Token Index: 831