Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.1344. Min Act: -0.1700
Data Index: 6026370 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.1344. Min Act: -0.1700
Data Index: 1385998 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.1344. Min Act: -0.1700
Data Index: 4603506 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.1344. Min Act: -0.1700
Data Index: 3211573 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.1031. Min Act: -0.1700
Data Index: 705627 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.1031. Min Act: -0.1700
Data Index: 2306185 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.0406. Min Act: -0.1700
Data Index: 1038239 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.0406. Min Act: -0.1699
Data Index: 70185 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.0094. Min Act: -0.1700
Data Index: 2306186 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.0094. Min Act: -0.1700
Data Index: 7786722 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.0094. Min Act: -0.1700
Data Index: 6766098 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1344. Min Range: -6.1344
Max Act: 6.0094. Min Act: -0.1700
Data Index: 1408650 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9781. Min Act: -0.1700
Data Index: 8284674 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9781. Min Act: -0.1700
Data Index: 6211218 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9469. Min Act: -0.1700
Data Index: 7640077 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9469. Min Act: -0.1700
Data Index: 1293445 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9469. Min Act: -0.1700
Data Index: 8503642 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9469. Min Act: -0.1700
Data Index: 4761318 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9469. Min Act: -0.1700
Data Index: 6136506 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1344. Min Range: -6.1344
Max Act: 5.9156. Min Act: -0.1700
Data Index: 4529333 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19