Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 712 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.3902. Min Act: -0.0000

Data Index: 184964 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2107. Min Act: -0.0000

Data Index: 518523 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.1846. Min Act: -0.0000

Data Index: 224640 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.0886. Min Act: -0.0000

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.8089. Min Act: -0.0000

Data Index: 910522 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.0851. Min Act: -0.0000

Data Index: 1061949 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.0972. Min Act: -0.0000

Data Index: 125854 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.8366. Min Act: -0.0000

Data Index: 826910 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.7021. Min Act: -0.0000

Data Index: 51012 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.6164. Min Act: -0.0000

Data Index: 859941 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.9199. Min Act: -0.0000

Data Index: 341672 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.0039. Min Act: -0.0000

Data Index: 88848 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.6958. Min Act: -0.0000

Data Index: 742863 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.7948. Min Act: -0.0000

Data Index: 104716 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.6521. Min Act: -0.0000

Data Index: 357277 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.6511. Min Act: -0.0000

Data Index: 731089 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.5336. Min Act: -0.0000

Data Index: 790953 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.6103. Min Act: -0.0000

Data Index: 694914 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.4991. Min Act: -0.0000

Data Index: 841358 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 2.3902. Min Range: -2.3902

Max Act: 1.4626. Min Act: -0.0000

Data Index: 15990 (C4 (Web Text))

Max Activating Token Index: 235