Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1076 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0006

Data Index: 675280 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0313. Min Act: -0.0006

Data Index: 743297 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0313. Min Act: -0.0005

Data Index: 126 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1329072 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0310. Min Act: -0.0005

Data Index: 548453 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0305. Min Act: -0.0005

Data Index: 19374 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0309. Min Act: -0.0005

Data Index: 162759 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0302. Min Act: -0.0005

Data Index: 1115981 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0289. Min Act: -0.0005

Data Index: 788907 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0294. Min Act: -0.0005

Data Index: 778934 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0293. Min Act: -0.0005

Data Index: 19689 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1075688 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0285. Min Act: -0.0005

Data Index: 1050554 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1329738 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0289. Min Act: -0.0006

Data Index: 778465 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0284. Min Act: -0.0005

Data Index: 199545 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0286. Min Act: -0.0006

Data Index: 719784 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0281. Min Act: -0.0005

Data Index: 23874 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0284. Min Act: -0.0005

Data Index: 282365 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0281. Min Act: -0.0005

Data Index: 713120 (C4 (Web Text))

Max Activating Token Index: 494