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

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

Neuron 3310 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.2143. Min Act: -0.0000

Data Index: 739533 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.2116. Min Act: -0.0000

Data Index: 164353 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1939. Min Act: -0.0000

Data Index: 960149 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1781. Min Act: -0.0000

Data Index: 452782 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1181005 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1787. Min Act: -0.0001

Data Index: 562968 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1784. Min Act: -0.0000

Data Index: 86508 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1078868 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1734. Min Act: -0.0000

Data Index: 514300 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1797. Min Act: -0.0000

Data Index: 597501 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1684. Min Act: -0.0000

Data Index: 807734 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1274435 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1684. Min Act: -0.0000

Data Index: 315437 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1511. Min Act: -0.0001

Data Index: 266053 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1535. Min Act: -0.0000

Data Index: 116686 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1097004 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1586. Min Act: -0.0000

Data Index: 778661 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1420. Min Act: -0.0000

Data Index: 145248 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1567. Min Act: -0.0000

Data Index: 674510 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.2143. Min Range: -0.2143

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1273287 (C4 (Web Text))

Max Activating Token Index: 329