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

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

Neuron 2844 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4656. Min Act: -0.0002

Data Index: 1476671 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4545. Min Act: -0.0002

Data Index: 1415822 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4846. Min Act: -0.0002

Data Index: 1541349 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4476. Min Act: -0.0002

Data Index: 1580091 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4576. Min Act: -0.0002

Data Index: 1384900 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4648. Min Act: -0.0002

Data Index: 1586223 (Python Code)

Max Activating Token Index: 360

Text #6

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4488. Min Act: -0.0002

Data Index: 1429147 (Python Code)

Max Activating Token Index: 461

Text #7

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4638. Min Act: -0.0002

Data Index: 1647491 (Python Code)

Max Activating Token Index: 283

Text #8

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4355. Min Act: -0.0002

Data Index: 1437900 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4157. Min Act: -0.0002

Data Index: 1464346 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3941. Min Act: -0.0002

Data Index: 1433153 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4024. Min Act: -0.0002

Data Index: 1516490 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4094. Min Act: -0.0002

Data Index: 1366622 (Python Code)

Max Activating Token Index: 317

Text #13

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3956. Min Act: -0.0002

Data Index: 1458732 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.4021. Min Act: -0.0002

Data Index: 1522755 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3875. Min Act: -0.0002

Data Index: 1449376 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3879. Min Act: -0.0002

Data Index: 1557861 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3792. Min Act: -0.0002

Data Index: 1522040 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3792. Min Act: -0.0002

Data Index: 1414001 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.4846. Min Range: -0.4846

Max Act: 0.3802. Min Act: -0.0002

Data Index: 1649218 (Python Code)

Max Activating Token Index: 18