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

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

Neuron 2126 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.5232. Min Act: -0.0001

Data Index: 1226073 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.2648. Min Act: -0.0001

Data Index: 1213840 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.1346. Min Act: -0.0001

Data Index: 1045756 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9803. Min Act: -0.0001

Data Index: 391508 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0698. Min Act: -0.0001

Data Index: 1332010 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0133. Min Act: -0.0001

Data Index: 625971 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.7265. Min Act: -0.0001

Data Index: 116841 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9874. Min Act: -0.0001

Data Index: 678515 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.1056. Min Act: -0.0001

Data Index: 900592 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9576. Min Act: -0.0001

Data Index: 1053773 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9793. Min Act: -0.0001

Data Index: 115018 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9667. Min Act: -0.0001

Data Index: 467962 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9510. Min Act: -0.0001

Data Index: 616775 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9342. Min Act: -0.0001

Data Index: 662404 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9438. Min Act: -0.0001

Data Index: 139255 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9102. Min Act: -0.0001

Data Index: 1332139 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9137. Min Act: -0.0001

Data Index: 1144599 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1163055 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.8669. Min Act: -0.0001

Data Index: 327012 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9433. Min Act: -0.0001

Data Index: 996839 (C4 (Web Text))

Max Activating Token Index: 1006