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

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

Neuron 3304 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.7952. Min Act: -0.0000

Data Index: 106210 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1206851 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6800. Min Act: -0.0000

Data Index: 521889 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6318. Min Act: -0.0000

Data Index: 650720 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5987. Min Act: -0.0000

Data Index: 265208 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1352285 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1179007 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5440. Min Act: -0.0000

Data Index: 972289 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4924. Min Act: -0.0000

Data Index: 244841 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5211. Min Act: -0.0000

Data Index: 484347 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5441. Min Act: -0.0000

Data Index: 436386 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4900. Min Act: -0.0000

Data Index: 667459 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1129079 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4796. Min Act: -0.0000

Data Index: 814841 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1197030 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4502. Min Act: -0.0000

Data Index: 186373 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1058259 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1217024 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4406. Min Act: -0.0000

Data Index: 13439 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1135670 (C4 (Web Text))

Max Activating Token Index: 435