Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2960 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5326. Min Act: -0.0004

Data Index: 580817 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5111. Min Act: -0.0004

Data Index: 1616751 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4799. Min Act: -0.0004

Data Index: 404287 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5163. Min Act: -0.0004

Data Index: 179319 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5064. Min Act: -0.0004

Data Index: 246415 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4713. Min Act: -0.0004

Data Index: 376709 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4819. Min Act: -0.0004

Data Index: 1092287 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4697. Min Act: -0.0004

Data Index: 514370 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4019. Min Act: -0.0004

Data Index: 618884 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4950. Min Act: -0.0004

Data Index: 273510 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4314. Min Act: -0.0004

Data Index: 1496060 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5100. Min Act: -0.0004

Data Index: 1183500 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4432. Min Act: -0.0004

Data Index: 1655370 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4709. Min Act: -0.0004

Data Index: 382922 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4699. Min Act: -0.0004

Data Index: 443513 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4562. Min Act: -0.0004

Data Index: 1638505 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4461. Min Act: -0.0004

Data Index: 103218 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4421. Min Act: -0.0004

Data Index: 1439556 (Python Code)

Max Activating Token Index: 801

Text #18

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4428. Min Act: -0.0004

Data Index: 871806 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4613. Min Act: -0.0004

Data Index: 411561 (C4 (Web Text))

Max Activating Token Index: 339