Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2821 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0249. Min Range: -1.0249

Max Act: 1.0249. Min Act: -0.0001

Data Index: 865171 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.0249. Min Range: -1.0249

Max Act: 1.0208. Min Act: -0.0001

Data Index: 9977 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9216. Min Act: -0.0001

Data Index: 466974 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8808. Min Act: -0.0001

Data Index: 390813 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9080. Min Act: -0.0001

Data Index: 869645 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.0249. Min Range: -1.0249

Max Act: 1.0171. Min Act: -0.0001

Data Index: 92450 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8925. Min Act: -0.0001

Data Index: 728185 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8986. Min Act: -0.0001

Data Index: 767803 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8917. Min Act: -0.0001

Data Index: 693172 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7299. Min Act: -0.0001

Data Index: 973829 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9324. Min Act: -0.0001

Data Index: 1031190 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8514. Min Act: -0.0001

Data Index: 501856 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9217. Min Act: -0.0001

Data Index: 750494 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9458. Min Act: -0.0001

Data Index: 396745 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8974. Min Act: -0.0001

Data Index: 591085 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8215. Min Act: -0.0001

Data Index: 970320 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8361. Min Act: -0.0001

Data Index: 1255394 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8800. Min Act: -0.0001

Data Index: 152884 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8045. Min Act: -0.0001

Data Index: 959830 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9014. Min Act: -0.0001

Data Index: 484266 (C4 (Web Text))

Max Activating Token Index: 660