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

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

Neuron 401 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0049. Min Range: -5.0049

Max Act: 5.0049. Min Act: -0.1700

Data Index: 968743 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 5.0049. Min Range: -5.0049

Max Act: 5.0049. Min Act: -0.1700

Data Index: 697076 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.9424. Min Act: -0.1700

Data Index: 1228732 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8799. Min Act: -0.1700

Data Index: 813696 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.8799. Min Act: -0.1700

Data Index: 83224 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6924. Min Act: -0.1700

Data Index: 994633 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7237. Min Act: -0.1700

Data Index: 355058 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.7237. Min Act: -0.1700

Data Index: 1004305 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6924. Min Act: -0.1700

Data Index: 140596 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6612. Min Act: -0.1700

Data Index: 1231120 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6612. Min Act: -0.1700

Data Index: 412229 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6924. Min Act: -0.1700

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6924. Min Act: -0.1700

Data Index: 779121 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6612. Min Act: -0.1700

Data Index: 899439 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6299. Min Act: -0.1700

Data Index: 573651 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.5987. Min Act: -0.1700

Data Index: 1103439 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6299. Min Act: -0.1700

Data Index: 215561 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.6612. Min Act: -0.1700

Data Index: 864264 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.5987. Min Act: -0.1700

Data Index: 644900 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 5.0049. Min Range: -5.0049

Max Act: 4.5987. Min Act: -0.1700

Data Index: 409238 (C4 (Web Text))

Max Activating Token Index: 95