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

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

Neuron 1211 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: 3.8062. Min Range: -3.8062

Max Act: 3.8062. Min Act: -0.1700

Data Index: 341613 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.7123. Min Act: -0.1700

Data Index: 1041885 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.7436. Min Act: -0.1700

Data Index: 293021 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.7436. Min Act: -0.1700

Data Index: 955826 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.7749. Min Act: -0.1700

Data Index: 1328598 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6810. Min Act: -0.1700

Data Index: 779885 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.7123. Min Act: -0.1700

Data Index: 1138852 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.7123. Min Act: -0.1700

Data Index: 590006 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6810. Min Act: -0.1700

Data Index: 631517 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6810. Min Act: -0.1700

Data Index: 957265 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6497. Min Act: -0.1700

Data Index: 361628 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6497. Min Act: -0.1700

Data Index: 788046 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6497. Min Act: -0.1700

Data Index: 804581 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6184. Min Act: -0.1700

Data Index: 381594 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6184. Min Act: -0.1700

Data Index: 1350443 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6810. Min Act: -0.1700

Data Index: 216714 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6184. Min Act: -0.1700

Data Index: 664108 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6184. Min Act: -0.1700

Data Index: 354305 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6497. Min Act: -0.1700

Data Index: 986501 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 3.8062. Min Range: -3.8062

Max Act: 3.6497. Min Act: -0.1700

Data Index: 697480 (C4 (Web Text))

Max Activating Token Index: 251