Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1887 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.6000. Min Act: -0.1700

Data Index: 1656369 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.3812. Min Act: -0.1700

Data Index: 1486918 (Python Code)

Max Activating Token Index: 524

Text #2

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.1625. Min Act: -0.1700

Data Index: 1392977 (Python Code)

Max Activating Token Index: 594

Text #3

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.1312. Min Act: -0.1700

Data Index: 1375317 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.1312. Min Act: -0.1700

Data Index: 1493681 (Python Code)

Max Activating Token Index: 417

Text #5

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.0375. Min Act: -0.1700

Data Index: 1608774 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.1625. Min Act: -0.1700

Data Index: 1555949 (Python Code)

Max Activating Token Index: 423

Text #7

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.1937. Min Act: -0.1700

Data Index: 1481162 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.1312. Min Act: -0.1700

Data Index: 1371044 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.9750. Min Act: -0.1700

Data Index: 1385878 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.6625. Min Act: -0.1700

Data Index: 1477646 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.6937. Min Act: -0.1700

Data Index: 1620190 (Python Code)

Max Activating Token Index: 636

Text #12

Max Range: 9.6000. Min Range: -9.6000

Max Act: 9.0375. Min Act: -0.1700

Data Index: 1489185 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.7250. Min Act: -0.1700

Data Index: 1430986 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.5062. Min Act: -0.1700

Data Index: 1569326 (Python Code)

Max Activating Token Index: 753

Text #15

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.7562. Min Act: -0.1700

Data Index: 1507374 (Python Code)

Max Activating Token Index: 603

Text #16

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.7875. Min Act: -0.1700

Data Index: 1376436 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.6937. Min Act: -0.1700

Data Index: 1572253 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.6937. Min Act: -0.1700

Data Index: 1531300 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 9.6000. Min Range: -9.6000

Max Act: 8.5687. Min Act: -0.1700

Data Index: 1559320 (Python Code)

Max Activating Token Index: 521