Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 801 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.9726. Min Act: -0.1700
Data Index: 399793 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0038. Min Range: -7.0038
Max Act: 7.0038. Min Act: -0.1700
Data Index: 3304203 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.9413. Min Act: -0.1700
Data Index: 564176 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.8788. Min Act: -0.1700
Data Index: 6195052 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.8788. Min Act: -0.1700
Data Index: 3504356 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.8476. Min Act: -0.1700
Data Index: 8072964 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.7851. Min Act: -0.1700
Data Index: 7549253 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.7226. Min Act: -0.1700
Data Index: 3556631 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.7226. Min Act: -0.1700
Data Index: 2543650 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.7226. Min Act: -0.1700
Data Index: 567157 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.7226. Min Act: -0.1700
Data Index: 6633551 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.7226. Min Act: -0.1700
Data Index: 5144024 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.6288. Min Act: -0.1700
Data Index: 3209217 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.6288. Min Act: -0.1700
Data Index: 5608763 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.6288. Min Act: -0.1700
Data Index: 1198119 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.6288. Min Act: -0.1700
Data Index: 5498104 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.6288. Min Act: -0.1700
Data Index: 6509746 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.6288. Min Act: -0.1700
Data Index: 3676651 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.5976. Min Act: -0.1700
Data Index: 5128379 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.6288. Min Act: -0.1700
Data Index: 1860032 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19