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

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

Neuron 5231 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.8073. Min Act: -0.0001

Data Index: 1516760 (Python Code)

Max Activating Token Index: 303

Text #1

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.8196. Min Act: -0.0001

Data Index: 1616101 (Python Code)

Max Activating Token Index: 922

Text #2

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.9486. Min Act: -0.0001

Data Index: 1480965 (Python Code)

Max Activating Token Index: 876

Text #3

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.5755. Min Act: -0.0001

Data Index: 179813 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.7780. Min Act: -0.0001

Data Index: 1436287 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.3774. Min Act: -0.0001

Data Index: 916775 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.4127. Min Act: -0.0001

Data Index: 263666 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.3000. Min Act: -0.0001

Data Index: 1299811 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.2142. Min Act: -0.0001

Data Index: 812087 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.4370. Min Act: -0.0001

Data Index: 93087 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.4203. Min Act: -0.0001

Data Index: 504854 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.2913. Min Act: -0.0001

Data Index: 1411418 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.2476. Min Act: -0.0001

Data Index: 635871 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.2688. Min Act: -0.0001

Data Index: 1440787 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.1346. Min Act: -0.0001

Data Index: 1060185 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1396715 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.2742. Min Act: -0.0001

Data Index: 1429479 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.1324. Min Act: -0.0000

Data Index: 1568116 (Python Code)

Max Activating Token Index: 718

Text #18

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.2171. Min Act: -0.0001

Data Index: 1466643 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 1.9486. Min Range: -1.9486

Max Act: 1.3361. Min Act: -0.0001

Data Index: 1424624 (Python Code)

Max Activating Token Index: 917