Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2022 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1111. Min Act: -0.0005

Data Index: 1244211 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1065. Min Act: -0.0005

Data Index: 1047980 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1044. Min Act: -0.0005

Data Index: 1096355 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1008. Min Act: -0.0005

Data Index: 364360 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0966. Min Act: -0.0005

Data Index: 362232 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1039. Min Act: -0.0005

Data Index: 496167 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0952. Min Act: -0.0005

Data Index: 1256549 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.1043. Min Act: -0.0005

Data Index: 240984 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0941. Min Act: -0.0005

Data Index: 666951 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0860. Min Act: -0.0005

Data Index: 467717 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0945. Min Act: -0.0005

Data Index: 728900 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0939. Min Act: -0.0005

Data Index: 1028710 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0937. Min Act: -0.0005

Data Index: 1254284 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0930. Min Act: -0.0005

Data Index: 1093393 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0904. Min Act: -0.0005

Data Index: 692230 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0928. Min Act: -0.0005

Data Index: 954308 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0910. Min Act: -0.0005

Data Index: 1308260 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0975. Min Act: -0.0005

Data Index: 763925 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0936. Min Act: -0.0005

Data Index: 1312947 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0864. Min Act: -0.0005

Data Index: 909169 (C4 (Web Text))

Max Activating Token Index: 327