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

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

Neuron 2132 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: 1.0094. Min Range: -1.0094

Max Act: 1.0094. Min Act: -0.0001

Data Index: 301577 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9704. Min Act: -0.0000

Data Index: 483787 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9668. Min Act: -0.0000

Data Index: 627085 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1232406 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.9165. Min Act: -0.0000

Data Index: 919251 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8733. Min Act: -0.0000

Data Index: 798005 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8758. Min Act: -0.0001

Data Index: 1080650 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1245157 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8420. Min Act: -0.0001

Data Index: 1118786 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8375. Min Act: -0.0001

Data Index: 188398 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8063. Min Act: -0.0000

Data Index: 919410 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8210. Min Act: -0.0001

Data Index: 66613 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7841. Min Act: -0.0001

Data Index: 1037739 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8395. Min Act: -0.0000

Data Index: 405295 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1252572 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8181. Min Act: -0.0001

Data Index: 497498 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7939. Min Act: -0.0001

Data Index: 915568 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7629. Min Act: -0.0001

Data Index: 784849 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.8695. Min Act: -0.0001

Data Index: 1097746 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.0094. Min Range: -1.0094

Max Act: 0.7599. Min Act: -0.0000

Data Index: 572500 (C4 (Web Text))

Max Activating Token Index: 375