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

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

Neuron 541 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0668. Min Act: -0.0002

Data Index: 870112 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0709. Min Act: -0.0002

Data Index: 227050 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0712. Min Act: -0.0002

Data Index: 826005 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0596. Min Act: -0.0002

Data Index: 218488 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0672. Min Act: -0.0002

Data Index: 437992 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1219657 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0603. Min Act: -0.0001

Data Index: 537806 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0533. Min Act: -0.0001

Data Index: 84599 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0627. Min Act: -0.0002

Data Index: 377949 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0610. Min Act: -0.0002

Data Index: 133872 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1125841 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1140531 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0561. Min Act: -0.0002

Data Index: 832357 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1211952 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0587. Min Act: -0.0002

Data Index: 272367 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0565. Min Act: -0.0002

Data Index: 61060 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0570. Min Act: -0.0002

Data Index: 671776 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0604. Min Act: -0.0001

Data Index: 846525 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0569. Min Act: -0.0002

Data Index: 304892 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0547. Min Act: -0.0001

Data Index: 781757 (C4 (Web Text))

Max Activating Token Index: 49