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

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

Neuron 1508 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: 5.1079. Min Range: -5.1079

Max Act: 5.0767. Min Act: -0.1700

Data Index: 239670 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0454. Min Act: -0.1700

Data Index: 1067314 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0142. Min Act: -0.1700

Data Index: 50082 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0454. Min Act: -0.1700

Data Index: 379679 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0454. Min Act: -0.1700

Data Index: 714077 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.1079. Min Act: -0.1700

Data Index: 115312 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0142. Min Act: -0.1700

Data Index: 245322 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0142. Min Act: -0.1700

Data Index: 744112 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0454. Min Act: -0.1700

Data Index: 754530 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9829. Min Act: -0.1700

Data Index: 1124956 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9204. Min Act: -0.1700

Data Index: 432681 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9829. Min Act: -0.1700

Data Index: 561929 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9517. Min Act: -0.1700

Data Index: 673328 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.8892. Min Act: -0.1700

Data Index: 1325565 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9829. Min Act: -0.1700

Data Index: 304341 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9204. Min Act: -0.1700

Data Index: 241936 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9517. Min Act: -0.1700

Data Index: 1250082 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 5.1079. Min Range: -5.1079

Max Act: 5.0142. Min Act: -0.1700

Data Index: 124161 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9204. Min Act: -0.1700

Data Index: 870432 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 5.1079. Min Range: -5.1079

Max Act: 4.9829. Min Act: -0.1700

Data Index: 207868 (C4 (Web Text))

Max Activating Token Index: 641