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

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

Neuron 139 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2268. Min Act: -0.0000

Data Index: 244621 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2000. Min Act: -0.0000

Data Index: 761274 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1478153 (Python Code)

Max Activating Token Index: 452

Text #3

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1732. Min Act: -0.0000

Data Index: 38934 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1574. Min Act: -0.0000

Data Index: 518589 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1631. Min Act: -0.0000

Data Index: 124183 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1559. Min Act: -0.0000

Data Index: 678854 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1537. Min Act: -0.0000

Data Index: 400741 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1522. Min Act: -0.0000

Data Index: 808577 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1077764 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1496. Min Act: -0.0000

Data Index: 254467 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1427. Min Act: -0.0000

Data Index: 904531 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1153004 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1467. Min Act: -0.0000

Data Index: 332547 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1513. Min Act: -0.0000

Data Index: 297804 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1385. Min Act: -0.0000

Data Index: 771355 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1390. Min Act: -0.0000

Data Index: 837985 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1145739 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1427. Min Act: -0.0000

Data Index: 904068 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1464. Min Act: -0.0000

Data Index: 561705 (C4 (Web Text))

Max Activating Token Index: 806