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

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

Neuron 347 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: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1282865 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0657. Min Act: -0.0001

Data Index: 606467 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1224480 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0609. Min Act: -0.0001

Data Index: 148616 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1134189 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0605. Min Act: -0.0001

Data Index: 634801 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0576. Min Act: -0.0001

Data Index: 823382 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0599. Min Act: -0.0001

Data Index: 209243 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0502. Min Act: -0.0001

Data Index: 670145 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1207700 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0592. Min Act: -0.0001

Data Index: 500738 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1282631 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1042813 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1308057 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1160209 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0545. Min Act: -0.0001

Data Index: 684610 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0001

Data Index: 20404 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1017676 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0528. Min Act: -0.0001

Data Index: 33761 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0565. Min Act: -0.0001

Data Index: 893117 (C4 (Web Text))

Max Activating Token Index: 507