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

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

Neuron 5890 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1636176 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1487389 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1587113 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1511977 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1435648 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1616910 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1438470 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1440364 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1583036 (Python Code)

Max Activating Token Index: 462

Text #9

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1487675 (Python Code)

Max Activating Token Index: 245

Text #10

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1564956 (Python Code)

Max Activating Token Index: 813

Text #11

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1544685 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1480100 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1393170 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1403364 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5129. Min Act: -0.0000

Data Index: 948286 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1404860 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1374972 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1433188 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1624744 (Python Code)

Max Activating Token Index: 641