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

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

Neuron 1109 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7749. Min Act: -0.0002

Data Index: 1643570 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1586564 (Python Code)

Max Activating Token Index: 849

Text #2

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1490494 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5701. Min Act: -0.0001

Data Index: 1523673 (Python Code)

Max Activating Token Index: 917

Text #4

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1374321 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1540184 (Python Code)

Max Activating Token Index: 715

Text #6

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1438545 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1580854 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1424912 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1394708 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1579496 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6173. Min Act: -0.0001

Data Index: 1547987 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6468. Min Act: -0.0001

Data Index: 1591346 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1468059 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6635. Min Act: -0.0001

Data Index: 1583835 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6629. Min Act: -0.0001

Data Index: 1536686 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6807. Min Act: -0.0001

Data Index: 1431113 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6173. Min Act: -0.0001

Data Index: 1394022 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1599304 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1533459 (Python Code)

Max Activating Token Index: 851