Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 4446 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 2.1109. Min Range: -2.1109

Max Act: 2.1109. Min Act: -0.1700

Data Index: 7752891 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 2.1109. Min Range: -2.1109

Max Act: 2.0100. Min Act: -0.1700

Data Index: 4270255 (Open Web Text)

Max Activating Token Index: 158

Text #2

Max Range: 2.1109. Min Range: -2.1109

Max Act: 2.0100. Min Act: -0.1700

Data Index: 3126723 (Open Web Text)

Max Activating Token Index: 575

Text #3

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9762. Min Act: -0.1700

Data Index: 5419070 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9593. Min Act: -0.1700

Data Index: 734948 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9762. Min Act: -0.1700

Data Index: 2196714 (Open Web Text)

Max Activating Token Index: 207

Text #6

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9423. Min Act: -0.1700

Data Index: 6450408 (Open Web Text)

Max Activating Token Index: 203

Text #7

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9423. Min Act: -0.1700

Data Index: 6377227 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9423. Min Act: -0.1700

Data Index: 6068410 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9423. Min Act: -0.1700

Data Index: 8587982 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9253. Min Act: -0.1700

Data Index: 8628157 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9253. Min Act: -0.1700

Data Index: 6379296 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9082. Min Act: -0.1700

Data Index: 7536134 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9253. Min Act: -0.1700

Data Index: 6184912 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8912. Min Act: -0.1700

Data Index: 5378459 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9082. Min Act: -0.1700

Data Index: 3485614 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9082. Min Act: -0.1700

Data Index: 4419408 (Open Web Text)

Max Activating Token Index: 526

Text #17

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.9082. Min Act: -0.1700

Data Index: 7946439 (Open Web Text)

Max Activating Token Index: 150

Text #18

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8741. Min Act: -0.1700

Data Index: 7830152 (Open Web Text)

Max Activating Token Index: 175

Text #19

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8912. Min Act: -0.1700

Data Index: 8438835 (Open Web Text)

Max Activating Token Index: 466