Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 69 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.5843. Min Act: -0.1700

Data Index: 948357 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.5216. Min Act: -0.1700

Data Index: 1005569 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4903. Min Act: -0.1700

Data Index: 873858 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 366367 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 187904 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 895203 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 1278844 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 416550 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 964697 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 692074 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4589. Min Act: -0.1700

Data Index: 280775 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4276. Min Act: -0.1700

Data Index: 698344 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4276. Min Act: -0.1700

Data Index: 146538 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4276. Min Act: -0.1700

Data Index: 961653 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4276. Min Act: -0.1700

Data Index: 120139 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4276. Min Act: -0.1700

Data Index: 117719 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4276. Min Act: -0.1700

Data Index: 796538 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3962. Min Act: -0.1700

Data Index: 106343 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3962. Min Act: -0.1700

Data Index: 161873 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3962. Min Act: -0.1700

Data Index: 529890 (C4 (Web Text))

Max Activating Token Index: 459