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

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

Neuron 4545 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: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0001

Data Index: 99036 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1218. Min Act: -0.0001

Data Index: 285663 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1276. Min Act: -0.0001

Data Index: 947929 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1082577 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1301610 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1211. Min Act: -0.0001

Data Index: 352131 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1245. Min Act: -0.0001

Data Index: 784240 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1207. Min Act: -0.0001

Data Index: 661239 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1286549 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1122. Min Act: -0.0001

Data Index: 122863 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1002. Min Act: -0.0001

Data Index: 45327 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0987. Min Act: -0.0001

Data Index: 964353 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1012. Min Act: -0.0001

Data Index: 849709 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1163110 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1013. Min Act: -0.0000

Data Index: 355597 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0947. Min Act: -0.0001

Data Index: 46967 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1017. Min Act: -0.0000

Data Index: 297363 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1045486 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0946. Min Act: -0.0001

Data Index: 659498 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.0844. Min Act: -0.0001

Data Index: 523819 (C4 (Web Text))

Max Activating Token Index: 998