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

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

Neuron 1791 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: 2.3727. Min Range: -2.3727

Max Act: 2.3727. Min Act: -0.0000

Data Index: 1530516 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 2.3727. Min Range: -2.3727

Max Act: 2.0988. Min Act: -0.0000

Data Index: 1471396 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 2.3727. Min Range: -2.3727

Max Act: 2.0999. Min Act: -0.0000

Data Index: 1369758 (Python Code)

Max Activating Token Index: 813

Text #3

Max Range: 2.3727. Min Range: -2.3727

Max Act: 2.0636. Min Act: -0.0000

Data Index: 1379753 (Python Code)

Max Activating Token Index: 666

Text #4

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.7660. Min Act: -0.0000

Data Index: 1536631 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.7153. Min Act: -0.0000

Data Index: 1621573 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1393503 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.6748. Min Act: -0.0000

Data Index: 1606866 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.7274. Min Act: -0.0000

Data Index: 1620724 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1483528 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1443386 (Python Code)

Max Activating Token Index: 975

Text #11

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.6639. Min Act: -0.0000

Data Index: 1564235 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1599141 (Python Code)

Max Activating Token Index: 358

Text #13

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.4604. Min Act: -0.0000

Data Index: 1600563 (Python Code)

Max Activating Token Index: 174

Text #14

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1477811 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1406492 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.5916. Min Act: -0.0000

Data Index: 1441796 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1637983 (Python Code)

Max Activating Token Index: 984

Text #18

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1578477 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 2.3727. Min Range: -2.3727

Max Act: 1.4651. Min Act: -0.0000

Data Index: 1552103 (Python Code)

Max Activating Token Index: 666