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

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

Neuron 1006 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7725. Min Act: -0.0000

Data Index: 175346 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1225635 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7766. Min Act: -0.0000

Data Index: 239494 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7746. Min Act: -0.0001

Data Index: 1291529 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7157. Min Act: -0.0001

Data Index: 420143 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6661. Min Act: -0.0001

Data Index: 422674 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6835. Min Act: -0.0001

Data Index: 129405 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1333311 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6655. Min Act: -0.0001

Data Index: 891037 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6407. Min Act: -0.0000

Data Index: 992024 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6508. Min Act: -0.0001

Data Index: 1206022 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6268. Min Act: -0.0001

Data Index: 190106 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6564. Min Act: -0.0000

Data Index: 479664 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6568. Min Act: -0.0001

Data Index: 650646 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1103619 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6406. Min Act: -0.0001

Data Index: 413660 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6124. Min Act: -0.0001

Data Index: 542574 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.5915. Min Act: -0.0001

Data Index: 727833 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6194. Min Act: -0.0001

Data Index: 312943 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6019. Min Act: -0.0000

Data Index: 28391 (C4 (Web Text))

Max Activating Token Index: 536