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

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

Neuron 3221 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: 0.9769. Min Range: -0.9769

Max Act: 0.9748. Min Act: -0.0001

Data Index: 845858 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.9031. Min Act: -0.0001

Data Index: 623485 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.9370. Min Act: -0.0001

Data Index: 376649 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8445. Min Act: -0.0001

Data Index: 587357 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8827. Min Act: -0.0001

Data Index: 234654 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.9769. Min Act: -0.0001

Data Index: 167324 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.9655. Min Act: -0.0001

Data Index: 388297 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8676. Min Act: -0.0000

Data Index: 371894 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8475. Min Act: -0.0000

Data Index: 171399 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8180. Min Act: -0.0001

Data Index: 361127 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8427. Min Act: -0.0001

Data Index: 297042 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8123. Min Act: -0.0001

Data Index: 891305 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.7792. Min Act: -0.0001

Data Index: 715847 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.7778. Min Act: -0.0001

Data Index: 716053 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8210. Min Act: -0.0000

Data Index: 377052 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.7851. Min Act: -0.0001

Data Index: 828293 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1061313 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.7599. Min Act: -0.0001

Data Index: 789596 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.8331. Min Act: -0.0000

Data Index: 226902 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.9769. Min Range: -0.9769

Max Act: 0.7786. Min Act: -0.0000

Data Index: 121736 (C4 (Web Text))

Max Activating Token Index: 427