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

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

Neuron 1771 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: 0.8122. Min Range: -0.8122

Max Act: 0.8122. Min Act: -0.0001

Data Index: 717035 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.7835. Min Act: -0.0001

Data Index: 921259 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.7774. Min Act: -0.0001

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.7091. Min Act: -0.0001

Data Index: 637195 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.6706. Min Act: -0.0001

Data Index: 1118776 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.6802. Min Act: -0.0001

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.6749. Min Act: -0.0001

Data Index: 1203812 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.6605. Min Act: -0.0001

Data Index: 643263 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.6549. Min Act: -0.0001

Data Index: 510012 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.6634. Min Act: -0.0001

Data Index: 84733 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5856. Min Act: -0.0001

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5853. Min Act: -0.0001

Data Index: 748152 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5030. Min Act: -0.0001

Data Index: 683505 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5727. Min Act: -0.0001

Data Index: 279663 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5858. Min Act: -0.0001

Data Index: 687219 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5202. Min Act: -0.0001

Data Index: 1255660 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.6052. Min Act: -0.0001

Data Index: 897227 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5342. Min Act: -0.0001

Data Index: 132239 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5484. Min Act: -0.0001

Data Index: 19469 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.8122. Min Range: -0.8122

Max Act: 0.5104. Min Act: -0.0001

Data Index: 440403 (C4 (Web Text))

Max Activating Token Index: 290