Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 563 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1218. Min Act: -0.0006

Data Index: 309816 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1203. Min Act: -0.0006

Data Index: 210514 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1121. Min Act: -0.0006

Data Index: 1211779 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1166. Min Act: -0.0006

Data Index: 508945 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1174. Min Act: -0.0006

Data Index: 1209561 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1099. Min Act: -0.0006

Data Index: 914642 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1007. Min Act: -0.0006

Data Index: 1191191 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1126. Min Act: -0.0006

Data Index: 15192 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1074. Min Act: -0.0006

Data Index: 604101 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1008. Min Act: -0.0006

Data Index: 961718 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1005. Min Act: -0.0006

Data Index: 243747 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1065. Min Act: -0.0006

Data Index: 1215111 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1102. Min Act: -0.0006

Data Index: 441385 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1054. Min Act: -0.0006

Data Index: 583 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0972. Min Act: -0.0006

Data Index: 805753 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0964. Min Act: -0.0006

Data Index: 87527 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1006. Min Act: -0.0006

Data Index: 1340655 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0961. Min Act: -0.0006

Data Index: 1294273 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1037. Min Act: -0.0006

Data Index: 31103 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0999. Min Act: -0.0006

Data Index: 942444 (C4 (Web Text))

Max Activating Token Index: 74