Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1378 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.8270. Min Act: -0.1700

Data Index: 1437755 (Python Code)

Max Activating Token Index: 871

Text #1

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7958. Min Act: -0.1700

Data Index: 1420577 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.8270. Min Act: -0.1700

Data Index: 1376049 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7958. Min Act: -0.1700

Data Index: 1464355 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7333. Min Act: -0.1700

Data Index: 1380331 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7645. Min Act: -0.1700

Data Index: 1463937 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1395008 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1482680 (Python Code)

Max Activating Token Index: 632

Text #8

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1633947 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7333. Min Act: -0.1700

Data Index: 1650761 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1446332 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1474869 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1392262 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.6708. Min Act: -0.1700

Data Index: 1513572 (Python Code)

Max Activating Token Index: 566

Text #14

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.6708. Min Act: -0.1700

Data Index: 1475905 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1591639 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.7020. Min Act: -0.1700

Data Index: 1489861 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.6708. Min Act: -0.1700

Data Index: 1630616 (Python Code)

Max Activating Token Index: 655

Text #18

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.5770. Min Act: -0.1700

Data Index: 1528966 (Python Code)

Max Activating Token Index: 946

Text #19

Max Range: 5.8270. Min Range: -5.8270

Max Act: 5.6395. Min Act: -0.1700

Data Index: 1406789 (Python Code)

Max Activating Token Index: 139