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

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

Neuron 1857 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0003

Data Index: 215253 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0748. Min Act: -0.0003

Data Index: 72541 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0643. Min Act: -0.0003

Data Index: 969939 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0662. Min Act: -0.0003

Data Index: 66957 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0643. Min Act: -0.0003

Data Index: 845783 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0661. Min Act: -0.0003

Data Index: 911849 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1654869 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1559395 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0606. Min Act: -0.0003

Data Index: 269689 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1502549 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1485099 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1646918 (Python Code)

Max Activating Token Index: 506

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1546445 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1382338 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1158420 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1397548 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1611984 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1434115 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1403406 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1204666 (C4 (Web Text))

Max Activating Token Index: 736