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

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

Neuron 1448 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.7828. Min Act: -0.1700

Data Index: 439553 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.7202. Min Act: -0.1700

Data Index: 819602 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.7202. Min Act: -0.1700

Data Index: 294931 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.6889. Min Act: -0.1700

Data Index: 378756 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1527895 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1391741 (Python Code)

Max Activating Token Index: 461

Text #6

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1507477 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1492408 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1490750 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.6263. Min Act: -0.1700

Data Index: 1601452 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.6263. Min Act: -0.1700

Data Index: 1285661 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5636. Min Act: -0.1700

Data Index: 1360593 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5323. Min Act: -0.1700

Data Index: 593675 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5636. Min Act: -0.1700

Data Index: 694432 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5323. Min Act: -0.1700

Data Index: 663202 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5636. Min Act: -0.1700

Data Index: 16393 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1467315 (Python Code)

Max Activating Token Index: 673

Text #17

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1449408 (Python Code)

Max Activating Token Index: 616

Text #18

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1393156 (Python Code)

Max Activating Token Index: 633

Text #19

Max Range: 3.7828. Min Range: -3.7828

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1374817 (Python Code)

Max Activating Token Index: 685