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

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

Neuron 5436 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.6950. Min Act: -0.0000

Data Index: 114320 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.5612. Min Act: -0.0000

Data Index: 115468 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.2758. Min Act: -0.0000

Data Index: 676720 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.4025. Min Act: -0.0000

Data Index: 886083 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.2365. Min Act: -0.0000

Data Index: 860588 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.3433. Min Act: -0.0000

Data Index: 318558 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.2340. Min Act: -0.0000

Data Index: 560151 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.2169. Min Act: -0.0000

Data Index: 14204 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.1915. Min Act: -0.0000

Data Index: 1320687 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.0642. Min Act: -0.0000

Data Index: 1054085 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.1519. Min Act: -0.0000

Data Index: 968472 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.1045. Min Act: -0.0000

Data Index: 814120 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.0919. Min Act: -0.0000

Data Index: 292191 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.0919. Min Act: -0.0000

Data Index: 950079 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.0676. Min Act: -0.0000

Data Index: 328821 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 2.6950. Min Range: -2.6950

Max Act: 1.9670. Min Act: -0.0000

Data Index: 948720 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 2.6950. Min Range: -2.6950

Max Act: 2.0093. Min Act: -0.0000

Data Index: 175411 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 2.6950. Min Range: -2.6950

Max Act: 1.8727. Min Act: -0.0000

Data Index: 646156 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.6950. Min Range: -2.6950

Max Act: 1.9521. Min Act: -0.0000

Data Index: 930921 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 2.6950. Min Range: -2.6950

Max Act: 1.9561. Min Act: -0.0000

Data Index: 1031555 (C4 (Web Text))

Max Activating Token Index: 293