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

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

Neuron 1410 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: 8.2224. Min Range: -8.2224

Max Act: 8.2224. Min Act: -0.1700

Data Index: 1611100 (Python Code)

Max Activating Token Index: 510

Text #1

Max Range: 8.2224. Min Range: -8.2224

Max Act: 8.0349. Min Act: -0.1700

Data Index: 1638611 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.8474. Min Act: -0.1700

Data Index: 1534318 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.7849. Min Act: -0.1700

Data Index: 1378915 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.7849. Min Act: -0.1700

Data Index: 1396917 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1601712 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1360002 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1422748 (Python Code)

Max Activating Token Index: 617

Text #8

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.6599. Min Act: -0.1700

Data Index: 1416846 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1635040 (Python Code)

Max Activating Token Index: 799

Text #10

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1415647 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.7224. Min Act: -0.1700

Data Index: 1545066 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1637974 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1384470 (Python Code)

Max Activating Token Index: 816

Text #14

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5974. Min Act: -0.1700

Data Index: 1503385 (Python Code)

Max Activating Token Index: 979

Text #15

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5974. Min Act: -0.1700

Data Index: 1517081 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1592396 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5349. Min Act: -0.1700

Data Index: 1566645 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.5974. Min Act: -0.1700

Data Index: 1469488 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 8.2224. Min Range: -8.2224

Max Act: 7.4099. Min Act: -0.1700

Data Index: 1444776 (Python Code)

Max Activating Token Index: 911