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

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

Neuron 4982 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6991. Min Range: -2.6991

Max Act: 2.6991. Min Act: -0.0000

Data Index: 1420523 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 2.6991. Min Range: -2.6991

Max Act: 2.5979. Min Act: -0.0000

Data Index: 1623860 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 2.6991. Min Range: -2.6991

Max Act: 2.4052. Min Act: -0.0000

Data Index: 1453786 (Python Code)

Max Activating Token Index: 860

Text #3

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.9576. Min Act: -0.0000

Data Index: 1427233 (Python Code)

Max Activating Token Index: 342

Text #4

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.9745. Min Act: -0.0000

Data Index: 1491404 (Python Code)

Max Activating Token Index: 274

Text #5

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.6691. Min Act: -0.0000

Data Index: 1373307 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.7957. Min Act: -0.0000

Data Index: 1410026 (Python Code)

Max Activating Token Index: 823

Text #7

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1643835 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1480637 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.8009. Min Act: -0.0000

Data Index: 1385822 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.8654. Min Act: -0.0000

Data Index: 1504504 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1614151 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.7716. Min Act: -0.0000

Data Index: 1428082 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.7547. Min Act: -0.0000

Data Index: 1487193 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.5675. Min Act: -0.0000

Data Index: 1557795 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1647534 (Python Code)

Max Activating Token Index: 592

Text #16

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1430344 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1406333 (Python Code)

Max Activating Token Index: 463

Text #18

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.2717. Min Act: -0.0000

Data Index: 1625042 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 2.6991. Min Range: -2.6991

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1518482 (Python Code)

Max Activating Token Index: 189