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

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

Neuron 1829 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: 3.4488. Min Range: -3.4488

Max Act: 3.4488. Min Act: -0.1700

Data Index: 1432936 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1364654 (Python Code)

Max Activating Token Index: 597

Text #2

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3861. Min Act: -0.1700

Data Index: 1452841 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3233. Min Act: -0.1700

Data Index: 1635054 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3233. Min Act: -0.1700

Data Index: 1558995 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1651308 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2919. Min Act: -0.1700

Data Index: 1524360 (Python Code)

Max Activating Token Index: 926

Text #7

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2762. Min Act: -0.1700

Data Index: 1642666 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2919. Min Act: -0.1700

Data Index: 1462360 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2447. Min Act: -0.1700

Data Index: 1554718 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1419327 (Python Code)

Max Activating Token Index: 688

Text #11

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1569596 (Python Code)

Max Activating Token Index: 197

Text #12

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1418609 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1602987 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1647588 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1518652 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2290. Min Act: -0.1700

Data Index: 1446098 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2447. Min Act: -0.1700

Data Index: 1555041 (Python Code)

Max Activating Token Index: 487

Text #18

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2290. Min Act: -0.1700

Data Index: 1615601 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1608382 (Python Code)

Max Activating Token Index: 590