Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2121 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.5383. Min Act: -0.0000

Data Index: 808339 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.4467. Min Act: -0.0000

Data Index: 554987 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1067658 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1989. Min Act: -0.0000

Data Index: 60975 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2096. Min Act: -0.0000

Data Index: 541492 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2829. Min Act: -0.0000

Data Index: 745167 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1137121 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1558. Min Act: -0.0000

Data Index: 215550 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1444. Min Act: -0.0000

Data Index: 542080 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1482. Min Act: -0.0000

Data Index: 960719 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1785. Min Act: -0.0000

Data Index: 384502 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.0752. Min Act: -0.0000

Data Index: 909157 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.0950. Min Act: -0.0000

Data Index: 564258 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1230. Min Act: -0.0000

Data Index: 46790 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.0753. Min Act: -0.0000

Data Index: 138698 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1161653 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1792. Min Act: -0.0000

Data Index: 35466 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1394. Min Act: -0.0000

Data Index: 153804 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1254889 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.5383. Min Range: -1.5383

Max Act: 1.1092. Min Act: -0.0000

Data Index: 68314 (C4 (Web Text))

Max Activating Token Index: 83