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

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

Neuron 3918 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: 2.4841. Min Range: -2.4841

Max Act: 2.2489. Min Act: -0.0000

Data Index: 667491 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.4841. Min Act: -0.0000

Data Index: 693965 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.3075. Min Act: -0.0000

Data Index: 995723 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.0661. Min Act: -0.0000

Data Index: 461126 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.1603. Min Act: -0.0000

Data Index: 93393 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.1504. Min Act: -0.0000

Data Index: 1003660 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.4452. Min Act: -0.0000

Data Index: 821852 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 2.4841. Min Range: -2.4841

Max Act: 1.9148. Min Act: -0.0000

Data Index: 679166 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 2.4841. Min Range: -2.4841

Max Act: 1.9334. Min Act: -0.0000

Data Index: 1186528 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.2095. Min Act: -0.0000

Data Index: 774362 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 2.4841. Min Range: -2.4841

Max Act: 1.6517. Min Act: -0.0000

Data Index: 884042 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1086429 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.0840. Min Act: -0.0000

Data Index: 1396518 (Python Code)

Max Activating Token Index: 661

Text #13

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.2054. Min Act: -0.0000

Data Index: 309080 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.0306. Min Act: -0.0000

Data Index: 960789 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.1383. Min Act: -0.0000

Data Index: 1145234 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 2.4841. Min Range: -2.4841

Max Act: 1.9292. Min Act: -0.0000

Data Index: 625262 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 2.4841. Min Range: -2.4841

Max Act: 2.0089. Min Act: -0.0000

Data Index: 1278968 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 2.4841. Min Range: -2.4841

Max Act: 1.9080. Min Act: -0.0000

Data Index: 42054 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 2.4841. Min Range: -2.4841

Max Act: 1.9927. Min Act: -0.0000

Data Index: 167526 (C4 (Web Text))

Max Activating Token Index: 752