Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1806 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1396. Min Act: -0.0003

Data Index: 471235 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1116. Min Act: -0.0003

Data Index: 786141 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1089. Min Act: -0.0003

Data Index: 107580 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1034. Min Act: -0.0003

Data Index: 347892 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1019. Min Act: -0.0003

Data Index: 312820 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1002. Min Act: -0.0003

Data Index: 533618 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1007. Min Act: -0.0003

Data Index: 454087 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0980. Min Act: -0.0003

Data Index: 556103 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1004. Min Act: -0.0003

Data Index: 283165 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1011. Min Act: -0.0004

Data Index: 268185 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0957. Min Act: -0.0003

Data Index: 115364 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0947. Min Act: -0.0003

Data Index: 413123 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0928. Min Act: -0.0004

Data Index: 666501 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0937. Min Act: -0.0003

Data Index: 191855 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0940. Min Act: -0.0003

Data Index: 1057115 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0940. Min Act: -0.0003

Data Index: 1328828 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0952. Min Act: -0.0003

Data Index: 763048 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0909. Min Act: -0.0003

Data Index: 243403 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0987. Min Act: -0.0003

Data Index: 988005 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0940. Min Act: -0.0003

Data Index: 374511 (C4 (Web Text))

Max Activating Token Index: 171