Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.7000. Min Act: -0.1700
Data Index: 2171714 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.6375. Min Act: -0.1700
Data Index: 5536877 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.5750. Min Act: -0.1700
Data Index: 1520637 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.5438. Min Act: -0.1700
Data Index: 5554981 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.5125. Min Act: -0.1700
Data Index: 7214506 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.5125. Min Act: -0.1700
Data Index: 6221485 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4813. Min Act: -0.1700
Data Index: 7483161 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4813. Min Act: -0.1700
Data Index: 3182239 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4500. Min Act: -0.1700
Data Index: 8446302 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4500. Min Act: -0.1700
Data Index: 6637611 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4500. Min Act: -0.1700
Data Index: 6937082 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4500. Min Act: -0.1700
Data Index: 5406075 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4188. Min Act: -0.1700
Data Index: 431419 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4188. Min Act: -0.1700
Data Index: 3365928 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4188. Min Act: -0.1700
Data Index: 3790839 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.3563. Min Act: -0.1700
Data Index: 2699201 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.3875. Min Act: -0.1700
Data Index: 6166850 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.4188. Min Act: -0.1700
Data Index: 5270790 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.3563. Min Act: -0.1700
Data Index: 4468721 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7000. Min Range: -6.7000
Max Act: 6.3563. Min Act: -0.1700
Data Index: 4736739 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19