Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3322 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0003

Data Index: 344667 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 431955 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1353306 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 994605 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1269482 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1448042 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1649680 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1445674 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1612475 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1551868 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1364310 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1534774 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1397375 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1497250 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1496594 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1466314 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0003

Data Index: 212043 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0003

Data Index: 340697 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0002

Data Index: 391502 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0003

Data Index: 465521 (C4 (Web Text))

Max Activating Token Index: 1