Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3554 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.7734. Min Act: -0.0000

Data Index: 1420790 (Python Code)

Max Activating Token Index: 499

Text #1

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.6709. Min Act: -0.0000

Data Index: 1491372 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.6413. Min Act: -0.0000

Data Index: 1584333 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1631024 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1580874 (Python Code)

Max Activating Token Index: 599

Text #5

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.5958. Min Act: -0.0000

Data Index: 1515086 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1382101 (Python Code)

Max Activating Token Index: 472

Text #7

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1640623 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1496684 (Python Code)

Max Activating Token Index: 157

Text #9

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.1530. Min Act: -0.0000

Data Index: 596170 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.0649. Min Act: -0.0000

Data Index: 304133 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.0065. Min Act: -0.0000

Data Index: 340624 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.0138. Min Act: -0.0000

Data Index: 903560 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.1050. Min Act: -0.0000

Data Index: 630891 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 1.7734. Min Range: -1.7734

Max Act: 0.9920. Min Act: -0.0000

Data Index: 924921 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.7734. Min Range: -1.7734

Max Act: 0.9468. Min Act: -0.0000

Data Index: 760340 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.7734. Min Range: -1.7734

Max Act: 1.0148. Min Act: -0.0000

Data Index: 582713 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.7734. Min Range: -1.7734

Max Act: 0.9519. Min Act: -0.0000

Data Index: 566653 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 1.7734. Min Range: -1.7734

Max Act: 0.9004. Min Act: -0.0000

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.7734. Min Range: -1.7734

Max Act: 0.9368. Min Act: -0.0000

Data Index: 272599 (C4 (Web Text))

Max Activating Token Index: 821