Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1970 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.7623. Min Act: -0.0000

Data Index: 961309 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.6331. Min Act: -0.0000

Data Index: 922566 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1098637 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1166173 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1008207 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1091428 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3434. Min Act: -0.0000

Data Index: 342851 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3244. Min Act: -0.0000

Data Index: 303379 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1279845 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2772. Min Act: -0.0000

Data Index: 727214 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2999. Min Act: -0.0000

Data Index: 123251 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3049. Min Act: -0.0000

Data Index: 221989 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1625384 (Python Code)

Max Activating Token Index: 885

Text #13

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1196114 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1254211 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2753. Min Act: -0.0000

Data Index: 924600 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2678. Min Act: -0.0000

Data Index: 801677 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1308441 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2577. Min Act: -0.0000

Data Index: 684413 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1397948 (Python Code)

Max Activating Token Index: 657