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

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

Neuron 63 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2569. Min Act: -0.0003

Data Index: 739382 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2337. Min Act: -0.0003

Data Index: 1345766 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1987. Min Act: -0.0003

Data Index: 1060520 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1875. Min Act: -0.0003

Data Index: 527671 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1885. Min Act: -0.0003

Data Index: 874179 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1794. Min Act: -0.0003

Data Index: 373990 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1674. Min Act: -0.0003

Data Index: 738619 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1714. Min Act: -0.0003

Data Index: 931768 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1682. Min Act: -0.0002

Data Index: 1114443 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1669. Min Act: -0.0003

Data Index: 1090750 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1599. Min Act: -0.0002

Data Index: 575585 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1569. Min Act: -0.0003

Data Index: 205188 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1432. Min Act: -0.0003

Data Index: 948224 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1474. Min Act: -0.0003

Data Index: 537028 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1447. Min Act: -0.0003

Data Index: 574391 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1322. Min Act: -0.0002

Data Index: 1077889 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1315. Min Act: -0.0003

Data Index: 1272860 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1237. Min Act: -0.0003

Data Index: 407486 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1237. Min Act: -0.0003

Data Index: 1062633 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1214. Min Act: -0.0003

Data Index: 731397 (C4 (Web Text))

Max Activating Token Index: 31