Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1872 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0198. Min Range: -5.0198
Max Act: 5.0198. Min Act: -0.1700
Data Index: 7550175 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0198. Min Range: -5.0198
Max Act: 5.0198. Min Act: -0.1700
Data Index: 2916703 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0198. Min Range: -5.0198
Max Act: 5.0198. Min Act: -0.1700
Data Index: 3587880 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.9261. Min Act: -0.1700
Data Index: 3247891 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.8948. Min Act: -0.1700
Data Index: 1080931 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.8323. Min Act: -0.1700
Data Index: 7693032 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.8011. Min Act: -0.1700
Data Index: 6692885 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.8011. Min Act: -0.1700
Data Index: 8451455 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7386. Min Act: -0.1700
Data Index: 8781934 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7386. Min Act: -0.1700
Data Index: 1507637 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7386. Min Act: -0.1700
Data Index: 8072686 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7073. Min Act: -0.1700
Data Index: 3994653 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7386. Min Act: -0.1700
Data Index: 4016773 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7698. Min Act: -0.1700
Data Index: 7644292 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7386. Min Act: -0.1700
Data Index: 3113341 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7073. Min Act: -0.1700
Data Index: 6232039 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7073. Min Act: -0.1700
Data Index: 5949500 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7073. Min Act: -0.1700
Data Index: 6704383 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7073. Min Act: -0.1700
Data Index: 112215 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0198. Min Range: -5.0198
Max Act: 4.7073. Min Act: -0.1700
Data Index: 7683371 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19