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

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

Neuron 2464 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: 1.8560. Min Range: -1.8560

Max Act: 1.8560. Min Act: -0.0001

Data Index: 187326 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.5476. Min Act: -0.0001

Data Index: 127850 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.6404. Min Act: -0.0001

Data Index: 1325974 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.5228. Min Act: -0.0001

Data Index: 663246 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7068. Min Act: -0.0001

Data Index: 768461 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.5244. Min Act: -0.0001

Data Index: 862475 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.5141. Min Act: -0.0001

Data Index: 576674 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.4367. Min Act: -0.0001

Data Index: 645142 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.4336. Min Act: -0.0001

Data Index: 349006 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.3751. Min Act: -0.0001

Data Index: 266908 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2340. Min Act: -0.0001

Data Index: 1316153 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.4008. Min Act: -0.0001

Data Index: 327665 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2419. Min Act: -0.0001

Data Index: 489167 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.3824. Min Act: -0.0001

Data Index: 151328 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.3820. Min Act: -0.0001

Data Index: 586350 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.1628. Min Act: -0.0001

Data Index: 205926 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2138. Min Act: -0.0001

Data Index: 559494 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2682. Min Act: -0.0001

Data Index: 969776 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2359. Min Act: -0.0001

Data Index: 874261 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.2557. Min Act: -0.0001

Data Index: 583930 (C4 (Web Text))

Max Activating Token Index: 470