Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1576 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.4760. Min Act: -0.1700

Data Index: 1449390 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.4135. Min Act: -0.1700

Data Index: 1416470 (Python Code)

Max Activating Token Index: 478

Text #2

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.3823. Min Act: -0.1700

Data Index: 1463118 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.3510. Min Act: -0.1700

Data Index: 1639446 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.3510. Min Act: -0.1700

Data Index: 1456368 (Python Code)

Max Activating Token Index: 787

Text #5

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.3510. Min Act: -0.1700

Data Index: 1593386 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.3198. Min Act: -0.1700

Data Index: 1630225 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.3666. Min Act: -0.1700

Data Index: 1584378 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2729. Min Act: -0.1700

Data Index: 1492630 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2416. Min Act: -0.1700

Data Index: 1360570 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2260. Min Act: -0.1700

Data Index: 1611028 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2416. Min Act: -0.1700

Data Index: 1534694 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2260. Min Act: -0.1700

Data Index: 1392584 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2104. Min Act: -0.1700

Data Index: 1593251 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.1791. Min Act: -0.1700

Data Index: 1607051 (Python Code)

Max Activating Token Index: 420

Text #15

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2416. Min Act: -0.1700

Data Index: 1418815 (Python Code)

Max Activating Token Index: 444

Text #16

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2260. Min Act: -0.1700

Data Index: 1447963 (Python Code)

Max Activating Token Index: 164

Text #17

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2104. Min Act: -0.1700

Data Index: 1552609 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.2104. Min Act: -0.1700

Data Index: 1394631 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 5.4760. Min Range: -5.4760

Max Act: 5.1791. Min Act: -0.1700

Data Index: 1590957 (Python Code)

Max Activating Token Index: 739