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

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

Neuron 2056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.7072. Min Act: -0.0003

Data Index: 413892 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6580. Min Act: -0.0003

Data Index: 14959 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6618. Min Act: -0.0003

Data Index: 1046362 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6796. Min Act: -0.0003

Data Index: 600314 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6356. Min Act: -0.0003

Data Index: 834504 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.7281. Min Act: -0.0003

Data Index: 606290 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6541. Min Act: -0.0003

Data Index: 386799 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6589. Min Act: -0.0003

Data Index: 1193302 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6362. Min Act: -0.0003

Data Index: 850538 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6516. Min Act: -0.0003

Data Index: 903166 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6676. Min Act: -0.0003

Data Index: 892159 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6456. Min Act: -0.0003

Data Index: 321097 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6255. Min Act: -0.0003

Data Index: 1272448 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6365. Min Act: -0.0003

Data Index: 1261270 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6613. Min Act: -0.0003

Data Index: 628715 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6812. Min Act: -0.0003

Data Index: 321575 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6371. Min Act: -0.0003

Data Index: 721050 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6333. Min Act: -0.0003

Data Index: 1188827 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.6563. Min Act: -0.0003

Data Index: 131670 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.7281. Min Range: -0.7281

Max Act: 0.7025. Min Act: -0.0003

Data Index: 1114579 (C4 (Web Text))

Max Activating Token Index: 697