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

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

Neuron 1004 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: 1.0619. Min Range: -1.0619

Max Act: 1.0619. Min Act: -0.0004

Data Index: 961945 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.9521. Min Act: -0.0003

Data Index: 105415 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.9389. Min Act: -0.0003

Data Index: 1106260 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.9623. Min Act: -0.0003

Data Index: 63295 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.7946. Min Act: -0.0003

Data Index: 822438 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8851. Min Act: -0.0003

Data Index: 1071974 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8619. Min Act: -0.0003

Data Index: 730499 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8300. Min Act: -0.0003

Data Index: 666956 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8065. Min Act: -0.0004

Data Index: 209958 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8703. Min Act: -0.0003

Data Index: 458569 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8474. Min Act: -0.0003

Data Index: 1069477 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8310. Min Act: -0.0003

Data Index: 1073494 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.7216. Min Act: -0.0003

Data Index: 310070 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.7106. Min Act: -0.0003

Data Index: 398993 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8528. Min Act: -0.0003

Data Index: 870356 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.6786. Min Act: -0.0003

Data Index: 85236 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.7946. Min Act: -0.0003

Data Index: 596025 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.7652. Min Act: -0.0003

Data Index: 855340 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.7564. Min Act: -0.0003

Data Index: 681434 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.0619. Min Range: -1.0619

Max Act: 0.8218. Min Act: -0.0003

Data Index: 144103 (C4 (Web Text))

Max Activating Token Index: 691