Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3196 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0002

Data Index: 1457210 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1618178 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0002

Data Index: 1641638 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1367300 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1654236 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1639046 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1474466 (Python Code)

Max Activating Token Index: 418

Text #7

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1423133 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1585520 (Python Code)

Max Activating Token Index: 801

Text #9

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1430663 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1568882 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1592816 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1507310 (Python Code)

Max Activating Token Index: 64

Text #13

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1481334 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1374282 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1414198 (Python Code)

Max Activating Token Index: 692

Text #16

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1616994 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1419744 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1491974 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1416128 (Python Code)

Max Activating Token Index: 306