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

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

Neuron 2616 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.9294. Min Act: -0.0003

Data Index: 673397 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.9199. Min Act: -0.0003

Data Index: 173948 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7846. Min Act: -0.0003

Data Index: 34688 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8256. Min Act: -0.0003

Data Index: 595531 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8121. Min Act: -0.0003

Data Index: 876641 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.8002. Min Act: -0.0003

Data Index: 872572 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.7351. Min Act: -0.0003

Data Index: 90736 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.6844. Min Act: -0.0003

Data Index: 1027614 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.6538. Min Act: -0.0003

Data Index: 695073 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.6179. Min Act: -0.0003

Data Index: 979790 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5963. Min Act: -0.0003

Data Index: 1267585 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5724. Min Act: -0.0003

Data Index: 1015102 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5635. Min Act: -0.0003

Data Index: 743415 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5154. Min Act: -0.0003

Data Index: 624136 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5832. Min Act: -0.0003

Data Index: 1163181 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5741. Min Act: -0.0003

Data Index: 651697 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5217. Min Act: -0.0003

Data Index: 324249 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5551. Min Act: -0.0003

Data Index: 19035 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.5121. Min Act: -0.0003

Data Index: 327655 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.9294. Min Range: -0.9294

Max Act: 0.4912. Min Act: -0.0003

Data Index: 707063 (C4 (Web Text))

Max Activating Token Index: 314