Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3659 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0002

Data Index: 549306 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0738. Min Act: -0.0002

Data Index: 446402 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0701. Min Act: -0.0001

Data Index: 377617 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0694. Min Act: -0.0002

Data Index: 443549 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0648. Min Act: -0.0002

Data Index: 766026 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0550. Min Act: -0.0001

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0625. Min Act: -0.0002

Data Index: 416832 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0617. Min Act: -0.0002

Data Index: 801582 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1335614 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0562. Min Act: -0.0001

Data Index: 538365 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0602. Min Act: -0.0001

Data Index: 636041 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1166352 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0570. Min Act: -0.0002

Data Index: 69615 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0566. Min Act: -0.0002

Data Index: 113744 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0585. Min Act: -0.0002

Data Index: 317483 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1005227 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0599. Min Act: -0.0002

Data Index: 225481 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0595. Min Act: -0.0002

Data Index: 114392 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1056040 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 204