Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1304 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.2252. Min Act: -0.0001

Data Index: 1647289 (Python Code)

Max Activating Token Index: 839

Text #1

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1646. Min Act: -0.0001

Data Index: 1533958 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1255. Min Act: -0.0001

Data Index: 1508656 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1389121 (Python Code)

Max Activating Token Index: 522

Text #4

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1749. Min Act: -0.0001

Data Index: 1564992 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0383. Min Act: -0.0001

Data Index: 1496788 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1147. Min Act: -0.0001

Data Index: 1651570 (Python Code)

Max Activating Token Index: 522

Text #7

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1583884 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0631. Min Act: -0.0001

Data Index: 1395410 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1627677 (Python Code)

Max Activating Token Index: 832

Text #10

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0605. Min Act: -0.0001

Data Index: 1565919 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0910. Min Act: -0.0001

Data Index: 1378282 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1582. Min Act: -0.0001

Data Index: 1433847 (Python Code)

Max Activating Token Index: 573

Text #13

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1148. Min Act: -0.0001

Data Index: 1365028 (Python Code)

Max Activating Token Index: 939

Text #14

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1186. Min Act: -0.0001

Data Index: 1486792 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1524920 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1635612 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0800. Min Act: -0.0001

Data Index: 1635475 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0742. Min Act: -0.0001

Data Index: 1394063 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0907. Min Act: -0.0001

Data Index: 1439689 (Python Code)

Max Activating Token Index: 253