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

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

Neuron 1646 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: 3.7659. Min Range: -3.7659

Max Act: 3.7659. Min Act: -0.1700

Data Index: 1421334 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.7659. Min Act: -0.1700

Data Index: 1594146 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.7659. Min Act: -0.1700

Data Index: 1496405 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.7659. Min Act: -0.1700

Data Index: 1532418 (Python Code)

Max Activating Token Index: 495

Text #4

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.7189. Min Act: -0.1700

Data Index: 1416296 (Python Code)

Max Activating Token Index: 764

Text #5

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.7033. Min Act: -0.1700

Data Index: 1373500 (Python Code)

Max Activating Token Index: 411

Text #6

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1562949 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.7033. Min Act: -0.1700

Data Index: 1557501 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6720. Min Act: -0.1700

Data Index: 1508675 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6720. Min Act: -0.1700

Data Index: 1532411 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6720. Min Act: -0.1700

Data Index: 1447797 (Python Code)

Max Activating Token Index: 415

Text #11

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1616098 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6407. Min Act: -0.1700

Data Index: 1509792 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6407. Min Act: -0.1700

Data Index: 1464378 (Python Code)

Max Activating Token Index: 542

Text #14

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1544152 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6407. Min Act: -0.1700

Data Index: 1628685 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6250. Min Act: -0.1700

Data Index: 1600216 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6563. Min Act: -0.1700

Data Index: 1527850 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6720. Min Act: -0.1700

Data Index: 1499343 (Python Code)

Max Activating Token Index: 599

Text #19

Max Range: 3.7659. Min Range: -3.7659

Max Act: 3.6563. Min Act: -0.1700

Data Index: 1496261 (Python Code)

Max Activating Token Index: 489