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

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

Neuron 544 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1632626 (Python Code)

Max Activating Token Index: 534

Text #1

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.4952. Min Act: -0.0001

Data Index: 1440172 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1230391 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.1320. Min Act: -0.0000

Data Index: 893712 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.1315. Min Act: -0.0001

Data Index: 1446584 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1496685 (Python Code)

Max Activating Token Index: 594

Text #6

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1432066 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.0913. Min Act: -0.0000

Data Index: 214982 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.1012. Min Act: -0.0000

Data Index: 119966 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1452775 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 1.5108. Min Range: -1.5108

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1479543 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1527626 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.9804. Min Act: -0.0001

Data Index: 416577 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1411385 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.9961. Min Act: -0.0001

Data Index: 57723 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1466798 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1469238 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1428929 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1445248 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 1.5108. Min Range: -1.5108

Max Act: 0.9326. Min Act: -0.0000

Data Index: 321672 (C4 (Web Text))

Max Activating Token Index: 229