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

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

Neuron 1212 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.6519. Min Act: -0.0000

Data Index: 455455 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.5370. Min Act: -0.0000

Data Index: 417469 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4985. Min Act: -0.0000

Data Index: 572818 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4801. Min Act: -0.0000

Data Index: 158068 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4654. Min Act: -0.0000

Data Index: 992962 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1037963 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4673. Min Act: -0.0000

Data Index: 432802 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4621. Min Act: -0.0000

Data Index: 766973 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4183. Min Act: -0.0000

Data Index: 348113 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1256850 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4506. Min Act: -0.0000

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4562. Min Act: -0.0000

Data Index: 386552 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4441. Min Act: -0.0000

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1006005 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4241. Min Act: -0.0000

Data Index: 871382 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1335405 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4335. Min Act: -0.0000

Data Index: 338473 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1086133 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.3678. Min Act: -0.0000

Data Index: 654667 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1208523 (C4 (Web Text))

Max Activating Token Index: 215