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

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

Neuron 2533 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4925. Min Act: -0.0000

Data Index: 108590 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4769. Min Act: -0.0000

Data Index: 234566 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4966. Min Act: -0.0000

Data Index: 521447 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1606739 (Python Code)

Max Activating Token Index: 843

Text #4

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1097364 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1512900 (Python Code)

Max Activating Token Index: 961

Text #6

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1460721 (Python Code)

Max Activating Token Index: 877

Text #7

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1496178 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1480315 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1604210 (Python Code)

Max Activating Token Index: 851

Text #10

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1397042 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1474702 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3611. Min Act: -0.0000

Data Index: 725004 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1530026 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1623712 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1598755 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1439680 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1377610 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1370275 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1495453 (Python Code)

Max Activating Token Index: 42