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

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

Neuron 1558 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.9696. Min Act: -0.0000

Data Index: 316966 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.8503. Min Act: -0.0000

Data Index: 569486 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1611671 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1387193 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7991. Min Act: -0.0000

Data Index: 24207 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.8292. Min Act: -0.0000

Data Index: 737882 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.8534. Min Act: -0.0000

Data Index: 746829 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.8168. Min Act: 0.0001

Data Index: 353248 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1629088 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7659. Min Act: -0.0000

Data Index: 621352 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7736. Min Act: -0.0000

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.8306. Min Act: -0.0000

Data Index: 562784 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7653. Min Act: -0.0000

Data Index: 196840 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7368. Min Act: 0.0000

Data Index: 874454 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7559. Min Act: -0.0000

Data Index: 174004 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7438. Min Act: 0.0000

Data Index: 1055047 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7430. Min Act: 0.0000

Data Index: 236366 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7346. Min Act: -0.0000

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1496054 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7366. Min Act: -0.0000

Data Index: 309595 (C4 (Web Text))

Max Activating Token Index: 635