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

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

Neuron 1972 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0146. Min Range: -5.0146

Max Act: 5.0146. Min Act: -0.0000

Data Index: 1554135 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 5.0146. Min Range: -5.0146

Max Act: 4.0441. Min Act: -0.0000

Data Index: 1512533 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.6593. Min Act: -0.0000

Data Index: 1647912 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.4370. Min Act: -0.0000

Data Index: 1601702 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.5493. Min Act: -0.0000

Data Index: 1604822 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.5540. Min Act: -0.0000

Data Index: 1408792 (Python Code)

Max Activating Token Index: 927

Text #6

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.5039. Min Act: -0.0000

Data Index: 1502007 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.5038. Min Act: -0.0000

Data Index: 1536414 (Python Code)

Max Activating Token Index: 613

Text #8

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.0819. Min Act: -0.0000

Data Index: 1536106 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.3476. Min Act: -0.0000

Data Index: 1501819 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1545434 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.1415. Min Act: -0.0000

Data Index: 1486213 (Python Code)

Max Activating Token Index: 135

Text #12

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.1337. Min Act: -0.0000

Data Index: 1433611 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 5.0146. Min Range: -5.0146

Max Act: 2.9146. Min Act: -0.0000

Data Index: 1466129 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.0514. Min Act: -0.0000

Data Index: 1557312 (Python Code)

Max Activating Token Index: 260

Text #15

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.2032. Min Act: -0.0000

Data Index: 1432899 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.0201. Min Act: -0.0000

Data Index: 1371593 (Python Code)

Max Activating Token Index: 406

Text #17

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.0181. Min Act: -0.0000

Data Index: 1452936 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.1180. Min Act: -0.0000

Data Index: 1421711 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 5.0146. Min Range: -5.0146

Max Act: 3.1106. Min Act: -0.0000

Data Index: 1410221 (Python Code)

Max Activating Token Index: 661