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

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

Neuron 4412 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0911. Min Act: -0.0000

Data Index: 653001 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1622183 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1604921 (Python Code)

Max Activating Token Index: 262

Text #3

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1109608 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0640. Min Act: -0.0000

Data Index: 429865 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0585. Min Act: -0.0000

Data Index: 78572 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1147846 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0523. Min Act: -0.0000

Data Index: 151109 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1644579 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1581004 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0503. Min Act: -0.0000

Data Index: 180077 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0534. Min Act: -0.0000

Data Index: 854867 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1229869 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1497651 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0441. Min Act: -0.0000

Data Index: 354590 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0456. Min Act: -0.0000

Data Index: 930353 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0520. Min Act: -0.0000

Data Index: 365098 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1383356 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0474. Min Act: -0.0000

Data Index: 621034 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1529353 (Python Code)

Max Activating Token Index: 461