Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 31 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0002

Data Index: 502637 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0002

Data Index: 769572 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0595. Min Act: 0.0001

Data Index: 269873 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1212917 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1085279 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1134606 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0569. Min Act: -0.0002

Data Index: 776775 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1193314 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1345102 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0562. Min Act: 0.0000

Data Index: 894460 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0552. Min Act: -0.0001

Data Index: 825735 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0577. Min Act: -0.0002

Data Index: 583320 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0563. Min Act: -0.0002

Data Index: 542860 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0547. Min Act: -0.0000

Data Index: 536190 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0520. Min Act: -0.0002

Data Index: 290084 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1293289 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0539. Min Act: -0.0000

Data Index: 841871 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0551. Min Act: -0.0002

Data Index: 99901 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0534. Min Act: -0.0001

Data Index: 471624 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0524. Min Act: 0.0001

Data Index: 566736 (C4 (Web Text))

Max Activating Token Index: 958