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

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

Neuron 860 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: 3.9970. Min Range: -3.9970

Max Act: 3.9970. Min Act: -0.1700

Data Index: 314291 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.8719. Min Act: -0.1700

Data Index: 220946 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.9345. Min Act: -0.1700

Data Index: 155453 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.8406. Min Act: -0.1700

Data Index: 517745 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.8719. Min Act: -0.1700

Data Index: 329898 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.8719. Min Act: -0.1700

Data Index: 1092076 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7781. Min Act: -0.1700

Data Index: 274054 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.8094. Min Act: -0.1700

Data Index: 1324459 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.8094. Min Act: -0.1700

Data Index: 68907 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7781. Min Act: -0.1700

Data Index: 875086 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7781. Min Act: -0.1700

Data Index: 832773 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7781. Min Act: -0.1700

Data Index: 750226 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7468. Min Act: -0.1700

Data Index: 217902 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7468. Min Act: -0.1700

Data Index: 582934 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7155. Min Act: -0.1700

Data Index: 6439 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7155. Min Act: -0.1700

Data Index: 411831 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.7155. Min Act: -0.1700

Data Index: 560915 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.6842. Min Act: -0.1700

Data Index: 395694 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.6842. Min Act: -0.1700

Data Index: 1015064 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 3.9970. Min Range: -3.9970

Max Act: 3.6529. Min Act: -0.1700

Data Index: 930155 (C4 (Web Text))

Max Activating Token Index: 529