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

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

Neuron 2501 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0002

Data Index: 127325 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 415085 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 500041 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 784968 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 764487 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 461469 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 290062 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 767047 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 768539 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 297169 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 194626 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 60910 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 846712 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1236973 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 426602 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 136972 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 304594 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1295774 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1222561 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 264025 (C4 (Web Text))

Max Activating Token Index: 144