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

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

Neuron 3482 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0003

Data Index: 597490 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0663. Min Act: -0.0003

Data Index: 118777 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0557. Min Act: -0.0003

Data Index: 533784 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0549. Min Act: -0.0003

Data Index: 136528 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1270872 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0538. Min Act: -0.0003

Data Index: 374085 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0535. Min Act: -0.0003

Data Index: 909889 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0528. Min Act: -0.0003

Data Index: 475597 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0518. Min Act: -0.0003

Data Index: 27489 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0521. Min Act: -0.0003

Data Index: 695807 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0525. Min Act: -0.0003

Data Index: 428890 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0510. Min Act: -0.0003

Data Index: 627265 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0527. Min Act: -0.0003

Data Index: 974489 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1178010 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0498. Min Act: -0.0003

Data Index: 530556 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0484. Min Act: -0.0003

Data Index: 215379 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0510. Min Act: -0.0003

Data Index: 817089 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0500. Min Act: -0.0003

Data Index: 869996 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0469. Min Act: -0.0003

Data Index: 34174 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1253943 (C4 (Web Text))

Max Activating Token Index: 518