Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8456. Min Act: -0.0000

Data Index: 331469 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1341988 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8179. Min Act: -0.0000

Data Index: 657043 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8634. Min Act: -0.0000

Data Index: 197721 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7810. Min Act: -0.0000

Data Index: 699379 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8317. Min Act: -0.0000

Data Index: 565505 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7411. Min Act: -0.0000

Data Index: 443037 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7581. Min Act: -0.0000

Data Index: 851629 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7512. Min Act: -0.0000

Data Index: 961333 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1003051 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7606. Min Act: -0.0000

Data Index: 646884 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6901. Min Act: -0.0000

Data Index: 887732 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6914. Min Act: -0.0000

Data Index: 537012 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6656. Min Act: -0.0000

Data Index: 361154 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1326371 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6866. Min Act: -0.0000

Data Index: 620146 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1097688 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6888. Min Act: -0.0000

Data Index: 662470 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6668. Min Act: -0.0000

Data Index: 696623 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1112603 (C4 (Web Text))

Max Activating Token Index: 687