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

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

Neuron 1711 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.8875. Min Act: -0.1700

Data Index: 1606242 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.7311. Min Act: -0.1700

Data Index: 1583285 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6685. Min Act: -0.1700

Data Index: 1571634 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6998. Min Act: -0.1700

Data Index: 1537875 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6685. Min Act: -0.1700

Data Index: 1546878 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1436666 (Python Code)

Max Activating Token Index: 802

Text #6

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1477545 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6059. Min Act: -0.1700

Data Index: 1377584 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1475425 (Python Code)

Max Activating Token Index: 285

Text #9

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1456994 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1421417 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5746. Min Act: -0.1700

Data Index: 1636505 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1509256 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1495262 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1547720 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1699

Data Index: 1586260 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1551117 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5119. Min Act: -0.1700

Data Index: 1451198 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5119. Min Act: -0.1700

Data Index: 1558722 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1428649 (Python Code)

Max Activating Token Index: 370