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

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

Neuron 4949 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5950. Min Act: 0.0000

Data Index: 1504528 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1593253 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1497746 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4756. Min Act: 0.0001

Data Index: 1618608 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4648. Min Act: 0.0000

Data Index: 1424633 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4259. Min Act: 0.0000

Data Index: 1399863 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1407675 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1471565 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1368859 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1475314 (Python Code)

Max Activating Token Index: 545

Text #10

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1490714 (Python Code)

Max Activating Token Index: 975

Text #11

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1648161 (Python Code)

Max Activating Token Index: 592

Text #12

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1454057 (Python Code)

Max Activating Token Index: 910

Text #13

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1384559 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1644928 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1502160 (Python Code)

Max Activating Token Index: 363

Text #16

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1362729 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1362095 (Python Code)

Max Activating Token Index: 376

Text #18

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1656401 (Python Code)

Max Activating Token Index: 319

Text #19

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1464458 (Python Code)

Max Activating Token Index: 157