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

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

Neuron 4478 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.6700. Min Act: -0.0000

Data Index: 661763 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.6783. Min Act: -0.0000

Data Index: 198682 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.6065. Min Act: -0.0000

Data Index: 706927 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.6695. Min Act: -0.0000

Data Index: 175758 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5925. Min Act: -0.0000

Data Index: 837393 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5540. Min Act: -0.0000

Data Index: 205560 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5646. Min Act: -0.0000

Data Index: 508354 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5593. Min Act: -0.0000

Data Index: 144907 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5432. Min Act: -0.0000

Data Index: 326552 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1219713 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5862. Min Act: -0.0000

Data Index: 713790 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5550. Min Act: -0.0000

Data Index: 102660 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1194181 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5387. Min Act: -0.0000

Data Index: 140539 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1291991 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5432. Min Act: -0.0000

Data Index: 664960 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5256. Min Act: -0.0000

Data Index: 712765 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1166376 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1145459 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1321333 (C4 (Web Text))

Max Activating Token Index: 306