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

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

Neuron 1609 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.8119. Min Act: -0.1700

Data Index: 437645 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.3431. Min Act: -0.1700

Data Index: 169436 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.2806. Min Act: -0.1700

Data Index: 821575 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.1869. Min Act: -0.1700

Data Index: 919223 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.2181. Min Act: -0.1700

Data Index: 346332 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.2181. Min Act: -0.1700

Data Index: 1013818 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.1869. Min Act: -0.1700

Data Index: 1058650 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.1556. Min Act: -0.1700

Data Index: 84401 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.1556. Min Act: -0.1700

Data Index: 1240798 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.1556. Min Act: -0.1700

Data Index: 1141524 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0931. Min Act: -0.1700

Data Index: 1219214 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0931. Min Act: -0.1700

Data Index: 933750 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0931. Min Act: -0.1700

Data Index: 639837 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0931. Min Act: -0.1700

Data Index: 1253763 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0931. Min Act: -0.1700

Data Index: 85378 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0619. Min Act: -0.1700

Data Index: 557018 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0619. Min Act: -0.1700

Data Index: 1208647 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0619. Min Act: -0.1700

Data Index: 1433682 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0619. Min Act: -0.1700

Data Index: 1580854 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 5.8119. Min Range: -5.8119

Max Act: 5.0306. Min Act: -0.1700

Data Index: 795667 (C4 (Web Text))

Max Activating Token Index: 445