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

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

Neuron 5844 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0001

Data Index: 993806 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0662. Min Act: -0.0001

Data Index: 952868 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1116526 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0607. Min Act: -0.0001

Data Index: 927180 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0617. Min Act: -0.0001

Data Index: 250801 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0605. Min Act: -0.0001

Data Index: 22876 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0584. Min Act: -0.0001

Data Index: 451540 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0584. Min Act: -0.0001

Data Index: 855545 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0574. Min Act: -0.0001

Data Index: 285120 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1296302 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0571. Min Act: -0.0001

Data Index: 426515 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0575. Min Act: -0.0001

Data Index: 771532 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0581. Min Act: -0.0001

Data Index: 969811 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0571. Min Act: -0.0001

Data Index: 753405 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0555. Min Act: -0.0001

Data Index: 326116 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0556. Min Act: -0.0001

Data Index: 357000 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0569. Min Act: -0.0001

Data Index: 422427 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0552. Min Act: -0.0001

Data Index: 798059 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0555. Min Act: -0.0001

Data Index: 624187 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0551. Min Act: -0.0001

Data Index: 942562 (C4 (Web Text))

Max Activating Token Index: 558