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

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

Neuron 4055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1661. Min Act: -0.0000

Data Index: 392253 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1533. Min Act: -0.0000

Data Index: 588710 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1509. Min Act: -0.0000

Data Index: 350298 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1021362 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1514. Min Act: -0.0000

Data Index: 685524 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1412. Min Act: -0.0000

Data Index: 101833 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1165313 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1376. Min Act: -0.0000

Data Index: 343699 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1167820 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1343145 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1287. Min Act: -0.0000

Data Index: 764387 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1139502 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1032312 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1300. Min Act: -0.0001

Data Index: 222728 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1294. Min Act: -0.0000

Data Index: 7023 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1303. Min Act: -0.0000

Data Index: 572776 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1348379 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1240396 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1186. Min Act: -0.0000

Data Index: 564865 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1206. Min Act: -0.0000

Data Index: 976379 (C4 (Web Text))

Max Activating Token Index: 61