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

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

Neuron 4764 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1920. Min Act: -0.0000

Data Index: 133480 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1223296 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.3183. Min Act: -0.0000

Data Index: 529571 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1306446 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.2118. Min Act: -0.0000

Data Index: 663471 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1153942 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1834. Min Act: -0.0000

Data Index: 707879 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1277826 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.2072. Min Act: -0.0000

Data Index: 507109 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.2042. Min Act: -0.0000

Data Index: 229330 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1139522 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1224068 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1067. Min Act: -0.0000

Data Index: 535983 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1373. Min Act: -0.0000

Data Index: 75081 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1116202 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0735. Min Act: -0.0000

Data Index: 125409 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1589521 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1278167 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1014. Min Act: -0.0000

Data Index: 120676 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0448. Min Act: -0.0000

Data Index: 847566 (C4 (Web Text))

Max Activating Token Index: 370