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

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

Neuron 1487 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: 3.8589. Min Range: -3.8589

Max Act: 3.8589. Min Act: -0.1700

Data Index: 607318 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.7963. Min Act: -0.1700

Data Index: 454636 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.7650. Min Act: -0.1700

Data Index: 126474 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.7963. Min Act: -0.1700

Data Index: 205753 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.7650. Min Act: -0.1700

Data Index: 1320773 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.7024. Min Act: -0.1700

Data Index: 303700 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.7024. Min Act: -0.1700

Data Index: 234465 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.7024. Min Act: -0.1700

Data Index: 162580 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.6085. Min Act: -0.1700

Data Index: 212240 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.5772. Min Act: -0.1700

Data Index: 749380 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.5459. Min Act: -0.1700

Data Index: 251044 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.5146. Min Act: -0.1700

Data Index: 262320 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.5146. Min Act: -0.1700

Data Index: 1280087 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.4832. Min Act: -0.1700

Data Index: 755135 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.5146. Min Act: -0.1700

Data Index: 755189 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.4519. Min Act: -0.1700

Data Index: 922158 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.4832. Min Act: -0.1700

Data Index: 1150825 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.4519. Min Act: -0.1700

Data Index: 222855 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.4519. Min Act: -0.1700

Data Index: 891417 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.8589. Min Range: -3.8589

Max Act: 3.4832. Min Act: -0.1700

Data Index: 460115 (C4 (Web Text))

Max Activating Token Index: 1023