Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1244 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0791. Min Act: -0.0002

Data Index: 712929 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1225276 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0684. Min Act: -0.0002

Data Index: 207244 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0651. Min Act: -0.0002

Data Index: 45019 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0598. Min Act: -0.0002

Data Index: 221189 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0595. Min Act: -0.0002

Data Index: 236746 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0596. Min Act: -0.0002

Data Index: 273351 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1033745 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1332113 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0590. Min Act: -0.0002

Data Index: 857482 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0568. Min Act: -0.0002

Data Index: 270299 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0599. Min Act: -0.0002

Data Index: 566064 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1274295 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0602. Min Act: -0.0002

Data Index: 407604 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0565. Min Act: -0.0002

Data Index: 570717 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0563. Min Act: -0.0002

Data Index: 799242 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0568. Min Act: -0.0002

Data Index: 70174 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0570. Min Act: -0.0002

Data Index: 734280 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1149698 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1267219 (C4 (Web Text))

Max Activating Token Index: 964