Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2656 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.0246. Min Range: -4.0246

Max Act: 4.0246. Min Act: -0.0001

Data Index: 888269 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 4.0246. Min Range: -4.0246

Max Act: 3.2068. Min Act: -0.0001

Data Index: 466818 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 4.0246. Min Range: -4.0246

Max Act: 3.0658. Min Act: -0.0000

Data Index: 553183 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.7211. Min Act: -0.0000

Data Index: 1016384 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.8536. Min Act: -0.0000

Data Index: 459462 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 4.0246. Min Range: -4.0246

Max Act: 3.0039. Min Act: -0.0000

Data Index: 968192 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.8807. Min Act: -0.0000

Data Index: 119664 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.7526. Min Act: -0.0000

Data Index: 558109 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.6963. Min Act: -0.0000

Data Index: 1332541 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.8317. Min Act: -0.0000

Data Index: 164423 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.7171. Min Act: -0.0001

Data Index: 1122417 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.8212. Min Act: -0.0001

Data Index: 422853 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.5551. Min Act: -0.0000

Data Index: 368602 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.6391. Min Act: -0.0001

Data Index: 647419 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.5252. Min Act: -0.0000

Data Index: 637900 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.5467. Min Act: -0.0001

Data Index: 637234 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.5281. Min Act: -0.0001

Data Index: 996745 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.4875. Min Act: -0.0000

Data Index: 796692 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.2490. Min Act: -0.0001

Data Index: 378333 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 4.0246. Min Range: -4.0246

Max Act: 2.2500. Min Act: -0.0001

Data Index: 923291 (C4 (Web Text))

Max Activating Token Index: 863