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

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

Neuron 2624 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4108. Min Act: -0.0001

Data Index: 1293564 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1348098 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4194. Min Act: -0.0001

Data Index: 1337014 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4342. Min Act: -0.0001

Data Index: 931482 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3998. Min Act: -0.0001

Data Index: 85363 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4684. Min Act: -0.0001

Data Index: 1334063 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1001863 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4026. Min Act: -0.0001

Data Index: 927018 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3937. Min Act: -0.0001

Data Index: 1138100 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4133. Min Act: -0.0001

Data Index: 585146 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4069. Min Act: -0.0001

Data Index: 192624 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3953. Min Act: -0.0001

Data Index: 284265 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3805. Min Act: -0.0001

Data Index: 921910 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3672. Min Act: -0.0001

Data Index: 426902 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3817. Min Act: -0.0001

Data Index: 1352145 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4165. Min Act: -0.0001

Data Index: 358596 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4570. Min Act: -0.0001

Data Index: 66496 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3662. Min Act: -0.0001

Data Index: 890441 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4080. Min Act: -0.0001

Data Index: 27449 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4095. Min Act: -0.0001

Data Index: 946440 (C4 (Web Text))

Max Activating Token Index: 770