Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5540 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.7126. Min Act: -0.1700
Data Index: 7036491 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.6501. Min Act: -0.1700
Data Index: 1875034 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.5251. Min Act: -0.1700
Data Index: 177379 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.5563. Min Act: -0.1700
Data Index: 5267849 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.5563. Min Act: -0.1700
Data Index: 2295448 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.5251. Min Act: -0.1700
Data Index: 7091187 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.5563. Min Act: -0.1700
Data Index: 8411973 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.5251. Min Act: -0.1700
Data Index: 3874283 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4938. Min Act: -0.1700
Data Index: 3504403 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4938. Min Act: -0.1700
Data Index: 7326426 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4626. Min Act: -0.1700
Data Index: 6842342 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4938. Min Act: -0.1699
Data Index: 1824913 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.5251. Min Act: -0.1700
Data Index: 1014405 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4938. Min Act: -0.1700
Data Index: 5718120 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4938. Min Act: -0.1700
Data Index: 6557830 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4626. Min Act: -0.1700
Data Index: 3756757 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4626. Min Act: -0.1700
Data Index: 3858127 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4626. Min Act: -0.1700
Data Index: 3999837 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4626. Min Act: -0.1700
Data Index: 6071285 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7126. Min Range: -5.7126
Max Act: 5.4626. Min Act: -0.1700
Data Index: 4084012 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19