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

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

Neuron 147 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: 0.1292. Min Range: -0.1292

Max Act: 0.1292. Min Act: -0.0001

Data Index: 688580 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1263960 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1273. Min Act: -0.0001

Data Index: 151104 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1187. Min Act: -0.0001

Data Index: 568074 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1186. Min Act: -0.0001

Data Index: 233679 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1109. Min Act: -0.0001

Data Index: 497294 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1310042 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1033. Min Act: -0.0001

Data Index: 811231 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1141. Min Act: -0.0001

Data Index: 434693 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1057. Min Act: -0.0001

Data Index: 269971 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1050133 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0896. Min Act: -0.0001

Data Index: 213821 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0975. Min Act: -0.0001

Data Index: 901995 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1059234 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0942. Min Act: -0.0001

Data Index: 954264 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0902. Min Act: -0.0001

Data Index: 718410 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0928. Min Act: -0.0001

Data Index: 675911 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0957. Min Act: -0.0001

Data Index: 605276 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0924. Min Act: -0.0001

Data Index: 113180 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0898. Min Act: -0.0001

Data Index: 863085 (C4 (Web Text))

Max Activating Token Index: 103