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

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

Neuron 3499 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1880. Min Range: -1.1880

Max Act: 1.1880. Min Act: -0.0001

Data Index: 259860 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.9866. Min Act: -0.0002

Data Index: 658982 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.8409. Min Act: -0.0002

Data Index: 1011912 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7987. Min Act: -0.0001

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7834. Min Act: -0.0001

Data Index: 447655 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.6998. Min Act: -0.0002

Data Index: 199989 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7038. Min Act: -0.0001

Data Index: 549619 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7865. Min Act: -0.0002

Data Index: 1326967 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7155. Min Act: -0.0002

Data Index: 1105641 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7158. Min Act: -0.0001

Data Index: 16032 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.6961. Min Act: -0.0002

Data Index: 886191 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.8024. Min Act: -0.0002

Data Index: 20224 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.6702. Min Act: -0.0002

Data Index: 441414 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.6802. Min Act: -0.0001

Data Index: 79590 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7250. Min Act: -0.0001

Data Index: 429921 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.6969. Min Act: -0.0002

Data Index: 795715 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.6805. Min Act: -0.0001

Data Index: 587357 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7370. Min Act: -0.0001

Data Index: 394678 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.6548. Min Act: -0.0002

Data Index: 361879 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.1880. Min Range: -1.1880

Max Act: 0.7097. Min Act: -0.0002

Data Index: 1177212 (C4 (Web Text))

Max Activating Token Index: 410