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

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

Neuron 1373 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.4797. Min Act: -0.1700

Data Index: 1430780 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.4484. Min Act: -0.1700

Data Index: 1613348 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.4484. Min Act: -0.1700

Data Index: 1443802 (Python Code)

Max Activating Token Index: 800

Text #3

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1634527 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3386. Min Act: -0.1700

Data Index: 877960 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3386. Min Act: -0.1700

Data Index: 1549749 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3386. Min Act: -0.1700

Data Index: 1583694 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3229. Min Act: -0.1700

Data Index: 1608948 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3072. Min Act: -0.1700

Data Index: 238881 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3386. Min Act: -0.1700

Data Index: 1540977 (Python Code)

Max Activating Token Index: 861

Text #10

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.3072. Min Act: -0.1700

Data Index: 1515504 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2915. Min Act: -0.1700

Data Index: 1539518 (Python Code)

Max Activating Token Index: 545

Text #12

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2915. Min Act: -0.1700

Data Index: 1632894 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1637980 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1404085 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2758. Min Act: -0.1699

Data Index: 1470146 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1311299 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2601. Min Act: -0.1700

Data Index: 401556 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2601. Min Act: -0.1700

Data Index: 1635293 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 3.4797. Min Range: -3.4797

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1435331 (Python Code)

Max Activating Token Index: 717