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

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

Neuron 4717 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1174675 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0668. Min Act: -0.0000

Data Index: 86030 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0636. Min Act: -0.0000

Data Index: 806181 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1175596 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0612. Min Act: -0.0001

Data Index: 708961 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0566. Min Act: -0.0000

Data Index: 453971 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1347721 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0556. Min Act: -0.0000

Data Index: 287699 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0515. Min Act: -0.0001

Data Index: 836727 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1214085 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0571. Min Act: -0.0000

Data Index: 664620 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1229895 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1179880 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0506. Min Act: -0.0000

Data Index: 221078 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0468. Min Act: -0.0000

Data Index: 661050 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0484. Min Act: -0.0000

Data Index: 44436 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0411. Min Act: -0.0000

Data Index: 416617 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0466. Min Act: -0.0000

Data Index: 881416 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0422. Min Act: -0.0000

Data Index: 427660 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0469. Min Act: -0.0000

Data Index: 689628 (C4 (Web Text))

Max Activating Token Index: 873