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

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

Neuron 1403 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1508310 (Python Code)

Max Activating Token Index: 207

Text #1

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.5259. Min Act: -0.1700

Data Index: 1538929 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4633. Min Act: -0.1700

Data Index: 747527 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4476. Min Act: -0.1700

Data Index: 1454930 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4319. Min Act: -0.1700

Data Index: 1461614 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4633. Min Act: -0.1700

Data Index: 1417204 (Python Code)

Max Activating Token Index: 725

Text #6

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4476. Min Act: -0.1700

Data Index: 1361089 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4319. Min Act: -0.1700

Data Index: 1361795 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4005. Min Act: -0.1700

Data Index: 1389164 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1644339 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4005. Min Act: -0.1700

Data Index: 244553 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4005. Min Act: -0.1700

Data Index: 1416933 (Python Code)

Max Activating Token Index: 820

Text #12

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1553679 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1651388 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.3692. Min Act: -0.1700

Data Index: 1588200 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.3692. Min Act: -0.1700

Data Index: 1561732 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.3849. Min Act: -0.1700

Data Index: 1500691 (Python Code)

Max Activating Token Index: 683

Text #17

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4005. Min Act: -0.1700

Data Index: 1589673 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1561716 (Python Code)

Max Activating Token Index: 411

Text #19

Max Range: 3.5729. Min Range: -3.5729

Max Act: 3.3849. Min Act: -0.1700

Data Index: 547471 (C4 (Web Text))

Max Activating Token Index: 273