Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 13 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1308571 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0456. Min Act: -0.0003

Data Index: 295715 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0445. Min Act: -0.0004

Data Index: 763961 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0459. Min Act: -0.0003

Data Index: 738653 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0448. Min Act: -0.0002

Data Index: 190043 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0417. Min Act: -0.0004

Data Index: 628476 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0420. Min Act: -0.0003

Data Index: 728776 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0410. Min Act: -0.0003

Data Index: 936617 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0412. Min Act: -0.0003

Data Index: 96432 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0412. Min Act: -0.0003

Data Index: 7016 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0417. Min Act: -0.0003

Data Index: 792875 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0421. Min Act: -0.0003

Data Index: 990293 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0391. Min Act: -0.0003

Data Index: 498564 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0406. Min Act: -0.0003

Data Index: 46352 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1316144 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1196526 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0384. Min Act: -0.0003

Data Index: 211154 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1069383 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0390. Min Act: -0.0003

Data Index: 933334 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1134526 (C4 (Web Text))

Max Activating Token Index: 9