Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4007 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1876. Min Range: -6.1876
Max Act: 6.1876. Min Act: -0.1700
Data Index: 1432474 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1876. Min Range: -6.1876
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6981435 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.9376. Min Act: -0.1700
Data Index: 8271569 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.9376. Min Act: -0.1700
Data Index: 2209517 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.9376. Min Act: -0.1700
Data Index: 4524635 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.9376. Min Act: -0.1700
Data Index: 900475 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.9064. Min Act: -0.1700
Data Index: 976551 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8751. Min Act: -0.1700
Data Index: 8551041 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8751. Min Act: -0.1700
Data Index: 5981103 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8751. Min Act: -0.1700
Data Index: 2804910 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.9064. Min Act: -0.1700
Data Index: 3404188 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8439. Min Act: -0.1700
Data Index: 6090911 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8439. Min Act: -0.1700
Data Index: 6543428 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8439. Min Act: -0.1700
Data Index: 3206584 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8126. Min Act: -0.1700
Data Index: 7269596 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.8126. Min Act: -0.1700
Data Index: 805813 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.7814. Min Act: -0.1700
Data Index: 4656056 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.7814. Min Act: -0.1700
Data Index: 8124425 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.7501. Min Act: -0.1700
Data Index: 3705023 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1876. Min Range: -6.1876
Max Act: 5.7814. Min Act: -0.1700
Data Index: 2414056 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19