Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4131 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.8394. Min Act: -0.0002

Data Index: 1582363 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6965. Min Act: -0.0002

Data Index: 1371976 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7357. Min Act: -0.0002

Data Index: 1485106 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6571. Min Act: -0.0002

Data Index: 1460505 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7081. Min Act: -0.0002

Data Index: 1401488 (Python Code)

Max Activating Token Index: 795

Text #5

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6358. Min Act: -0.0002

Data Index: 1493217 (Python Code)

Max Activating Token Index: 493

Text #6

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5924. Min Act: -0.0002

Data Index: 1589995 (Python Code)

Max Activating Token Index: 612

Text #7

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6488. Min Act: -0.0002

Data Index: 1587023 (Python Code)

Max Activating Token Index: 755

Text #8

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5824. Min Act: -0.0002

Data Index: 1653565 (Python Code)

Max Activating Token Index: 730

Text #9

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6307. Min Act: -0.0002

Data Index: 1562988 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6422. Min Act: -0.0002

Data Index: 1393394 (Python Code)

Max Activating Token Index: 694

Text #11

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6559. Min Act: -0.0002

Data Index: 1490793 (Python Code)

Max Activating Token Index: 682

Text #12

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6021. Min Act: -0.0002

Data Index: 1480809 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6421. Min Act: -0.0002

Data Index: 1590789 (Python Code)

Max Activating Token Index: 545

Text #14

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6046. Min Act: -0.0002

Data Index: 1457969 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6442. Min Act: -0.0002

Data Index: 1456914 (Python Code)

Max Activating Token Index: 691

Text #16

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6010. Min Act: -0.0002

Data Index: 1445110 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5730. Min Act: -0.0002

Data Index: 1376291 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5946. Min Act: -0.0002

Data Index: 1540320 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6308. Min Act: -0.0002

Data Index: 1503283 (Python Code)

Max Activating Token Index: 330