< Prev | Home | Model | Random | Next >

Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1607 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')



Text #0

Max Range: 9.7782. Min Range: -9.7782

Max Act: 9.7782. Min Act: -0.0005

Data Index: 1393252 (Python Code)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 9.7782. Min Range: -9.7782

Max Act: 9.6776. Min Act: -0.0005

Data Index: 1648698 (Python Code)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 9.7782. Min Range: -9.7782

Max Act: 9.0116. Min Act: -0.0005

Data Index: 1640972 (Python Code)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 9.7782. Min Range: -9.7782

Max Act: 8.9225. Min Act: -0.0005

Data Index: 1526467 (Python Code)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 9.7782. Min Range: -9.7782

Max Act: 8.8095. Min Act: -0.0005

Data Index: 1613207 (Python Code)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 9.7782. Min Range: -9.7782

Max Act: 8.5027. Min Act: -0.0005

Data Index: 1415581 (Python Code)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 9.7782. Min Range: -9.7782

Max Act: 8.0484. Min Act: -0.0005

Data Index: 1238765 (C4 (Web Text))

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 9.7782. Min Range: -9.7782

Max Act: 7.9999. Min Act: -0.0005

Data Index: 1651690 (Python Code)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 9.7782. Min Range: -9.7782

Max Act: 7.3492. Min Act: -0.0005

Data Index: 1634802 (Python Code)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.8467. Min Act: -0.0005

Data Index: 1610130 (Python Code)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.6947. Min Act: -0.0006

Data Index: 650453 (C4 (Web Text))

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.6333. Min Act: -0.0005

Data Index: 1449647 (Python Code)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.6224. Min Act: -0.0005

Data Index: 1569812 (Python Code)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.5918. Min Act: -0.0005

Data Index: 1620448 (Python Code)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.4471. Min Act: -0.0005

Data Index: 1587485 (Python Code)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.4370. Min Act: -0.0005

Data Index: 1421588 (Python Code)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.4180. Min Act: -0.0005

Data Index: 1575383 (Python Code)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.3615. Min Act: -0.0006

Data Index: 1556012 (Python Code)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.2779. Min Act: -0.0005

Data Index: 1539160 (Python Code)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 9.7782. Min Range: -9.7782

Max Act: 0.2922. Min Act: -0.0005

Data Index: 1587603 (Python Code)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #19