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

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

Neuron 3464 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1410243 (Python Code)

Max Activating Token Index: 657

Text #1

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1700. Min Act: -0.0000

Data Index: 82597 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1733. Min Act: -0.0000

Data Index: 244284 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1612340 (Python Code)

Max Activating Token Index: 581

Text #4

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1558362 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1605532 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1346128 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1147. Min Act: -0.0000

Data Index: 517774 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1516. Min Act: -0.0000

Data Index: 676870 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1349816 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1080965 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1432. Min Act: -0.0000

Data Index: 796293 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1384858 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1427. Min Act: -0.0000

Data Index: 511348 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1493. Min Act: -0.0000

Data Index: 82869 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1345. Min Act: -0.0000

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1378. Min Act: -0.0000

Data Index: 882571 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1388. Min Act: -0.0000

Data Index: 604497 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1451. Min Act: -0.0000

Data Index: 585588 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1313075 (C4 (Web Text))

Max Activating Token Index: 759