Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1037 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.9801. Min Act: -0.0001

Data Index: 1387282 (Python Code)

Max Activating Token Index: 348

Text #1

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.9756. Min Act: -0.0001

Data Index: 1464470 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8591. Min Act: -0.0001

Data Index: 1569348 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8894. Min Act: -0.0001

Data Index: 1635136 (Python Code)

Max Activating Token Index: 562

Text #4

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1387538 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8777. Min Act: -0.0001

Data Index: 1471834 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8870. Min Act: -0.0001

Data Index: 1600969 (Python Code)

Max Activating Token Index: 670

Text #7

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8520. Min Act: -0.0001

Data Index: 1618993 (Python Code)

Max Activating Token Index: 547

Text #8

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8342. Min Act: -0.0001

Data Index: 1406936 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1656987 (Python Code)

Max Activating Token Index: 647

Text #10

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1465914 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8134. Min Act: -0.0001

Data Index: 1465952 (Python Code)

Max Activating Token Index: 427

Text #12

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1403237 (Python Code)

Max Activating Token Index: 865

Text #13

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7527. Min Act: -0.0001

Data Index: 1533052 (Python Code)

Max Activating Token Index: 920

Text #14

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7824. Min Act: -0.0001

Data Index: 1614851 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7781. Min Act: -0.0001

Data Index: 1648318 (Python Code)

Max Activating Token Index: 1001

Text #16

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8107. Min Act: -0.0001

Data Index: 1587584 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8250. Min Act: -0.0001

Data Index: 1448844 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8681. Min Act: -0.0001

Data Index: 1483758 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7676. Min Act: -0.0001

Data Index: 1430201 (Python Code)

Max Activating Token Index: 1006