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

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

Neuron 824 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0000

Data Index: 782869 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1228029 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1074. Min Act: -0.0000

Data Index: 71176 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0953. Min Act: -0.0000

Data Index: 394155 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1077. Min Act: -0.0000

Data Index: 736129 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0993. Min Act: -0.0000

Data Index: 32056 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0895. Min Act: -0.0001

Data Index: 783441 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0944. Min Act: -0.0001

Data Index: 674441 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0952. Min Act: -0.0000

Data Index: 88754 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1176542 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1224736 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0938. Min Act: -0.0000

Data Index: 313691 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0886. Min Act: -0.0000

Data Index: 703308 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1210240 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1335476 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1104233 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1314238 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0726. Min Act: -0.0000

Data Index: 12596 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0864. Min Act: -0.0001

Data Index: 286091 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1238371 (C4 (Web Text))

Max Activating Token Index: 122