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

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

Neuron 3431 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: 0.7258. Min Range: -0.7258

Max Act: 0.7258. Min Act: -0.0001

Data Index: 1049006 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6975. Min Act: -0.0001

Data Index: 504390 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6484. Min Act: -0.0001

Data Index: 23952 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1045008 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6435. Min Act: -0.0001

Data Index: 939153 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.6925. Min Act: -0.0001

Data Index: 96089 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5451. Min Act: -0.0001

Data Index: 339523 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5397. Min Act: -0.0001

Data Index: 557694 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5271. Min Act: -0.0001

Data Index: 847776 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5590. Min Act: -0.0001

Data Index: 1212318 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5059. Min Act: -0.0001

Data Index: 1195000 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5268. Min Act: -0.0001

Data Index: 383992 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5192. Min Act: -0.0001

Data Index: 3819 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1098165 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.4997. Min Act: -0.0001

Data Index: 386096 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.4992. Min Act: -0.0001

Data Index: 649431 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5165. Min Act: -0.0001

Data Index: 523688 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.4760. Min Act: -0.0001

Data Index: 8217 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1256213 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.7258. Min Range: -0.7258

Max Act: 0.5045. Min Act: -0.0001

Data Index: 794471 (C4 (Web Text))

Max Activating Token Index: 34