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

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

Neuron 2105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1019. Min Act: -0.0001

Data Index: 668444 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1303100 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0987. Min Act: -0.0001

Data Index: 935155 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0966. Min Act: -0.0001

Data Index: 205961 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0916. Min Act: -0.0001

Data Index: 774744 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0900. Min Act: -0.0001

Data Index: 637046 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0969. Min Act: -0.0001

Data Index: 107933 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1149748 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0912. Min Act: -0.0001

Data Index: 432454 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1093305 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0865. Min Act: -0.0001

Data Index: 326494 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0833. Min Act: -0.0001

Data Index: 519667 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0811. Min Act: -0.0001

Data Index: 911060 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0830. Min Act: -0.0001

Data Index: 984092 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1280661 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1267486 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0916. Min Act: -0.0001

Data Index: 300803 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0890. Min Act: -0.0001

Data Index: 616463 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1182601 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0869. Min Act: -0.0001

Data Index: 134275 (C4 (Web Text))

Max Activating Token Index: 705