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

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

Neuron 1011 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.4383. Min Act: -0.1699

Data Index: 1406243 (Python Code)

Max Activating Token Index: 504

Text #1

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.2508. Min Act: -0.1700

Data Index: 1551394 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.1883. Min Act: -0.1700

Data Index: 1656338 (Python Code)

Max Activating Token Index: 591

Text #3

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.1258. Min Act: -0.1699

Data Index: 1517024 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.0008. Min Act: -0.1700

Data Index: 1373869 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.0008. Min Act: -0.1700

Data Index: 1428239 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.0633. Min Act: -0.1700

Data Index: 1634095 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.8758. Min Act: -0.1700

Data Index: 1377678 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.8758. Min Act: -0.1700

Data Index: 1465977 (Python Code)

Max Activating Token Index: 361

Text #9

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.9383. Min Act: -0.1699

Data Index: 1442585 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.0008. Min Act: -0.1699

Data Index: 1500190 (Python Code)

Max Activating Token Index: 453

Text #11

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.8758. Min Act: -0.1700

Data Index: 1600566 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 8.4383. Min Range: -8.4383

Max Act: 8.0008. Min Act: -0.1700

Data Index: 1652268 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.8133. Min Act: -0.1700

Data Index: 1436159 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.8133. Min Act: -0.1700

Data Index: 1541813 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.8133. Min Act: -0.1700

Data Index: 1535412 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.7508. Min Act: -0.1700

Data Index: 1569911 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.6883. Min Act: -0.1699

Data Index: 1611683 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.7508. Min Act: -0.1700

Data Index: 1613423 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 8.4383. Min Range: -8.4383

Max Act: 7.7508. Min Act: -0.1700

Data Index: 1475659 (Python Code)

Max Activating Token Index: 139