Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2664 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1807. Min Act: -0.0003

Data Index: 401390 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1694. Min Act: -0.0003

Data Index: 383521 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1560. Min Act: -0.0003

Data Index: 299603 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1437. Min Act: -0.0003

Data Index: 1167703 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1389. Min Act: -0.0003

Data Index: 860681 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1416. Min Act: -0.0003

Data Index: 152766 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1467. Min Act: -0.0003

Data Index: 1088716 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1454. Min Act: -0.0003

Data Index: 1336604 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1474. Min Act: -0.0003

Data Index: 387009 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1435. Min Act: -0.0003

Data Index: 307870 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1385. Min Act: -0.0003

Data Index: 1012108 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1325. Min Act: -0.0003

Data Index: 12836 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1321. Min Act: -0.0003

Data Index: 1313204 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1338. Min Act: -0.0003

Data Index: 299246 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1343. Min Act: -0.0003

Data Index: 225788 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1374. Min Act: -0.0003

Data Index: 1209607 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1439. Min Act: -0.0003

Data Index: 569156 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1346. Min Act: -0.0003

Data Index: 717603 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1294. Min Act: -0.0003

Data Index: 311190 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1333. Min Act: -0.0003

Data Index: 687158 (C4 (Web Text))

Max Activating Token Index: 66