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

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

Neuron 5557 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1271599 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1390355 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1035246 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1125362 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1383931 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1533. Min Act: -0.0001

Data Index: 34216 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1474. Min Act: -0.0001

Data Index: 743273 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1419. Min Act: -0.0000

Data Index: 197020 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1394. Min Act: -0.0001

Data Index: 79641 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1288. Min Act: -0.0001

Data Index: 966938 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1472. Min Act: -0.0001

Data Index: 253899 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1434. Min Act: -0.0001

Data Index: 405666 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1337. Min Act: -0.0001

Data Index: 203581 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1368. Min Act: -0.0001

Data Index: 645673 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1198720 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1234353 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1150. Min Act: -0.0001

Data Index: 671030 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1229. Min Act: -0.0001

Data Index: 198124 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1310826 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1411230 (Python Code)

Max Activating Token Index: 621