Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2188 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0243. Min Range: -1.0243

Max Act: 1.0243. Min Act: -0.0001

Data Index: 288576 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8849. Min Act: -0.0001

Data Index: 1245062 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9057. Min Act: -0.0001

Data Index: 316723 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8839. Min Act: -0.0001

Data Index: 392710 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9072. Min Act: -0.0001

Data Index: 53690 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9518. Min Act: -0.0001

Data Index: 873841 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8113. Min Act: -0.0001

Data Index: 27101 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7823. Min Act: -0.0001

Data Index: 673755 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8131. Min Act: -0.0001

Data Index: 950665 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8111. Min Act: -0.0001

Data Index: 890706 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7448. Min Act: -0.0001

Data Index: 931591 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8104. Min Act: -0.0001

Data Index: 343787 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8232. Min Act: -0.0001

Data Index: 328425 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7782. Min Act: -0.0001

Data Index: 154125 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8411. Min Act: -0.0001

Data Index: 977103 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7622. Min Act: -0.0001

Data Index: 652480 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7368. Min Act: -0.0001

Data Index: 584831 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8024. Min Act: -0.0001

Data Index: 1273377 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8224. Min Act: -0.0001

Data Index: 634709 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7707. Min Act: -0.0001

Data Index: 1086234 (C4 (Web Text))

Max Activating Token Index: 50