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

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

Neuron 3970 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: 1.0998. Min Range: -1.0998

Max Act: 1.0998. Min Act: -0.0000

Data Index: 801065 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.9436. Min Act: -0.0000

Data Index: 364060 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1623492 (Python Code)

Max Activating Token Index: 299

Text #3

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1492525 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8353. Min Act: -0.0000

Data Index: 761291 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8534. Min Act: -0.0000

Data Index: 685876 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1444555 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1444802 (Python Code)

Max Activating Token Index: 614

Text #8

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1656462 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8719. Min Act: -0.0000

Data Index: 249484 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1563812 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1484960 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1562812 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1644270 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.6807. Min Act: -0.0000

Data Index: 109217 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.7613. Min Act: -0.0000

Data Index: 77136 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1392490 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1584734 (Python Code)

Max Activating Token Index: 1019

Text #18

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1434149 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.0998. Min Range: -1.0998

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1380540 (Python Code)

Max Activating Token Index: 855