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

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

Neuron 5049 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.4599. Min Act: -0.0000

Data Index: 992582 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1160580 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.3233. Min Act: -0.0000

Data Index: 323910 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1046239 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.2300. Min Act: -0.0000

Data Index: 314949 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.3752. Min Act: -0.0000

Data Index: 790865 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.2268. Min Act: -0.0000

Data Index: 213519 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.2924. Min Act: -0.0000

Data Index: 289254 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.3045. Min Act: -0.0000

Data Index: 891008 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1525. Min Act: -0.0000

Data Index: 376825 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.2176. Min Act: -0.0000

Data Index: 1006927 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1367. Min Act: -0.0000

Data Index: 522740 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1676. Min Act: -0.0000

Data Index: 875788 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.3017. Min Act: -0.0000

Data Index: 68022 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.2484. Min Act: -0.0000

Data Index: 643934 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1400. Min Act: -0.0000

Data Index: 93211 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1330340 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.0595. Min Act: -0.0000

Data Index: 441183 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1267844 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.4599. Min Range: -1.4599

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1089867 (C4 (Web Text))

Max Activating Token Index: 544