Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5725 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1687. Min Range: -5.1687
Max Act: 5.1687. Min Act: -0.1700
Data Index: 4246763 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1687. Min Range: -5.1687
Max Act: 5.0437. Min Act: -0.1700
Data Index: 1149224 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1687. Min Range: -5.1687
Max Act: 5.0437. Min Act: -0.1700
Data Index: 318307 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1687. Min Range: -5.1687
Max Act: 5.0124. Min Act: -0.1700
Data Index: 3377428 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1687. Min Range: -5.1687
Max Act: 5.0124. Min Act: -0.1700
Data Index: 664585 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1687. Min Range: -5.1687
Max Act: 5.0124. Min Act: -0.1700
Data Index: 3377427 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9812. Min Act: -0.1700
Data Index: 8256922 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9812. Min Act: -0.1700
Data Index: 7035197 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9812. Min Act: -0.1700
Data Index: 6998418 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9812. Min Act: -0.1700
Data Index: 4246762 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9499. Min Act: -0.1700
Data Index: 2343795 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9499. Min Act: -0.1700
Data Index: 6016208 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9499. Min Act: -0.1700
Data Index: 6741004 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.8874. Min Act: -0.1700
Data Index: 7565361 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9187. Min Act: -0.1700
Data Index: 1986009 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9187. Min Act: -0.1700
Data Index: 2479237 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9187. Min Act: -0.1700
Data Index: 3049071 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9499. Min Act: -0.1700
Data Index: 455718 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9187. Min Act: -0.1700
Data Index: 2574791 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1687. Min Range: -5.1687
Max Act: 4.9187. Min Act: -0.1700
Data Index: 452857 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19