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

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

Neuron 5575 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0002

Data Index: 73208 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0499. Min Act: -0.0002

Data Index: 74932 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0462. Min Act: -0.0002

Data Index: 625753 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0435. Min Act: -0.0002

Data Index: 485496 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0425. Min Act: -0.0002

Data Index: 507319 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0423. Min Act: -0.0002

Data Index: 117102 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0399. Min Act: -0.0002

Data Index: 543307 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0406. Min Act: -0.0002

Data Index: 570720 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0389. Min Act: -0.0002

Data Index: 219662 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1348735 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0385. Min Act: -0.0002

Data Index: 173038 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1250353 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1178942 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1322508 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0361. Min Act: -0.0002

Data Index: 65274 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1215900 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0339. Min Act: -0.0002

Data Index: 431607 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0345. Min Act: -0.0002

Data Index: 140180 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1121090 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1123347 (C4 (Web Text))

Max Activating Token Index: 129