Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.8315. Min Act: -0.1700
Data Index: 4070051 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7377. Min Act: -0.1700
Data Index: 8482093 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7065. Min Act: -0.1700
Data Index: 3903948 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6752. Min Act: -0.1700
Data Index: 683189 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6752. Min Act: -0.1700
Data Index: 7143462 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6752. Min Act: -0.1700
Data Index: 8264197 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6752. Min Act: -0.1700
Data Index: 5016261 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6752. Min Act: -0.1700
Data Index: 1412271 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6127. Min Act: -0.1700
Data Index: 112797 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6127. Min Act: -0.1700
Data Index: 5631004 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6127. Min Act: -0.1700
Data Index: 7272088 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6127. Min Act: -0.1700
Data Index: 1758350 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6127. Min Act: -0.1700
Data Index: 1232202 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6127. Min Act: -0.1700
Data Index: 3873446 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6127. Min Act: -0.1700
Data Index: 742516 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5815. Min Act: -0.1700
Data Index: 512359 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5815. Min Act: -0.1700
Data Index: 1121858 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5815. Min Act: -0.1700
Data Index: 4671209 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5815. Min Act: -0.1700
Data Index: 5652137 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5502. Min Act: -0.1700
Data Index: 7146589 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19