Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 404 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0237. Min Range: -3.0237

Max Act: 3.0237. Min Act: -0.1700

Data Index: 474098 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.0237. Min Range: -3.0237

Max Act: 3.0237. Min Act: -0.1700

Data Index: 303067 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9921. Min Act: -0.1700

Data Index: 655511 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9921. Min Act: -0.1700

Data Index: 807895 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9763. Min Act: -0.1700

Data Index: 1110519 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9763. Min Act: -0.1700

Data Index: 984273 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9605. Min Act: -0.1700

Data Index: 1200550 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9763. Min Act: -0.1700

Data Index: 157649 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9446. Min Act: -0.1700

Data Index: 493759 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9288. Min Act: -0.1700

Data Index: 1105195 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9446. Min Act: -0.1700

Data Index: 1000535 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9446. Min Act: -0.1700

Data Index: 997104 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9446. Min Act: -0.1700

Data Index: 411616 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9446. Min Act: -0.1700

Data Index: 1134791 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9446. Min Act: -0.1700

Data Index: 975225 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9605. Min Act: -0.1700

Data Index: 1235119 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9446. Min Act: -0.1700

Data Index: 690622 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9288. Min Act: -0.1700

Data Index: 425721 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9288. Min Act: -0.1700

Data Index: 1108543 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 3.0237. Min Range: -3.0237

Max Act: 2.9129. Min Act: -0.1700

Data Index: 222033 (C4 (Web Text))

Max Activating Token Index: 278