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

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

Neuron 1826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.6575. Min Act: -0.1700

Data Index: 949871 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.6888. Min Act: -0.1700

Data Index: 998270 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.6262. Min Act: -0.1700

Data Index: 1044275 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.6575. Min Act: -0.1700

Data Index: 131964 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5949. Min Act: -0.1700

Data Index: 1065443 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5949. Min Act: -0.1700

Data Index: 1239319 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5949. Min Act: -0.1700

Data Index: 840017 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 54501 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5636. Min Act: -0.1700

Data Index: 61960 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5636. Min Act: -0.1700

Data Index: 28514 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1065433 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5009. Min Act: -0.1700

Data Index: 1067093 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5636. Min Act: -0.1700

Data Index: 757711 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1109336 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 152024 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 978799 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 830762 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 628967 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1028799 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 3.6888. Min Range: -3.6888

Max Act: 3.5323. Min Act: -0.1700

Data Index: 631008 (C4 (Web Text))

Max Activating Token Index: 403