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

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

Neuron 1389 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: 3.0778. Min Range: -3.0778

Max Act: 3.0778. Min Act: -0.1700

Data Index: 1459964 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 3.0778. Min Range: -3.0778

Max Act: 3.0620. Min Act: -0.1700

Data Index: 1365765 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 3.0778. Min Range: -3.0778

Max Act: 3.0305. Min Act: -0.1700

Data Index: 1544284 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 3.0778. Min Range: -3.0778

Max Act: 3.0147. Min Act: -0.1700

Data Index: 1646050 (Python Code)

Max Activating Token Index: 615

Text #4

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9989. Min Act: -0.1700

Data Index: 1561891 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9989. Min Act: -0.1700

Data Index: 1463927 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1649769 (Python Code)

Max Activating Token Index: 635

Text #7

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1637553 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1611992 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1392060 (Python Code)

Max Activating Token Index: 129

Text #10

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9989. Min Act: -0.1700

Data Index: 1622033 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1522699 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1564859 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1547591 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1470037 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1566011 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9514. Min Act: -0.1700

Data Index: 1556689 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1535060 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1385126 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 3.0778. Min Range: -3.0778

Max Act: 2.9355. Min Act: -0.1700

Data Index: 1490713 (Python Code)

Max Activating Token Index: 284