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

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

Neuron 3374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3651. Min Act: -0.0001

Data Index: 1383561 (Python Code)

Max Activating Token Index: 754

Text #1

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3724. Min Act: -0.0000

Data Index: 1469081 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1589326 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1643538 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1541627 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1505. Min Act: -0.0001

Data Index: 233485 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1141. Min Act: -0.0001

Data Index: 1415345 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2192. Min Act: -0.0001

Data Index: 1444727 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1570203 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1517849 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1633587 (Python Code)

Max Activating Token Index: 482

Text #11

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1631614 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1368137 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1446236 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0659. Min Act: -0.0001

Data Index: 1000388 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0884. Min Act: -0.0001

Data Index: 1451808 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0607. Min Act: -0.0001

Data Index: 1570592 (Python Code)

Max Activating Token Index: 685

Text #17

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0568. Min Act: -0.0001

Data Index: 1643020 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0800. Min Act: -0.0001

Data Index: 1363248 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0753. Min Act: -0.0001

Data Index: 1576994 (Python Code)

Max Activating Token Index: 721