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

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

Neuron 768 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: 3.1410. Min Range: -3.1410

Max Act: 3.1410. Min Act: -0.1700

Data Index: 589115 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1410. Min Act: -0.1700

Data Index: 66128 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1410. Min Act: -0.1700

Data Index: 786102 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1410. Min Act: -0.1700

Data Index: 1047245 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1407365 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1081660 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1166021 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 656802 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 18889 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 664575 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1322609 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 847023 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 628263 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 495106 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 100857 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1316512 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.0937. Min Act: -0.1700

Data Index: 625168 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.0779. Min Act: -0.1700

Data Index: 957706 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.0779. Min Act: -0.1700

Data Index: 521414 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.1410. Min Range: -3.1410

Max Act: 3.0622. Min Act: -0.1700

Data Index: 985219 (C4 (Web Text))

Max Activating Token Index: 29