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

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

Neuron 3683 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1325337 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.7964. Min Act: -0.0000

Data Index: 557908 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.7611. Min Act: -0.0000

Data Index: 584239 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.7303. Min Act: -0.0000

Data Index: 913821 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.7342. Min Act: -0.0000

Data Index: 150458 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.7150. Min Act: -0.0000

Data Index: 87200 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6902. Min Act: -0.0000

Data Index: 632464 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6971. Min Act: -0.0000

Data Index: 753017 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6889. Min Act: -0.0000

Data Index: 568547 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1131099 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6716. Min Act: -0.0000

Data Index: 672841 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6724. Min Act: -0.0000

Data Index: 885973 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6456. Min Act: -0.0000

Data Index: 993808 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1286273 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1020153 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1124829 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1352614 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6219. Min Act: -0.0000

Data Index: 371747 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1277602 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.9858. Min Range: -0.9858

Max Act: 0.6109. Min Act: -0.0000

Data Index: 894511 (C4 (Web Text))

Max Activating Token Index: 392