Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6473. Min Range: -7.6473
Max Act: 7.6473. Min Act: -0.1700
Data Index: 1217559 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6473. Min Range: -7.6473
Max Act: 7.1785. Min Act: -0.1700
Data Index: 1673934 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6473. Min Range: -7.6473
Max Act: 7.0223. Min Act: -0.1700
Data Index: 365548 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6473. Min Range: -7.6473
Max Act: 7.0223. Min Act: -0.1700
Data Index: 7996426 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6473. Min Range: -7.6473
Max Act: 7.0223. Min Act: -0.1700
Data Index: 4667123 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.9598. Min Act: -0.1700
Data Index: 5026015 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.9285. Min Act: -0.1700
Data Index: 5218108 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.8660. Min Act: -0.1700
Data Index: 1835931 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.8660. Min Act: -0.1700
Data Index: 4947695 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.8973. Min Act: -0.1700
Data Index: 7860422 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.7410. Min Act: -0.1700
Data Index: 6587672 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.7723. Min Act: -0.1700
Data Index: 1071656 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.7410. Min Act: -0.1700
Data Index: 7761373 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.7410. Min Act: -0.1700
Data Index: 6130119 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.7410. Min Act: -0.1700
Data Index: 3581689 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.6785. Min Act: -0.1700
Data Index: 453286 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.7098. Min Act: -0.1700
Data Index: 1362970 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.6785. Min Act: -0.1700
Data Index: 5548445 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.6473. Min Act: -0.1700
Data Index: 3766129 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6473. Min Range: -7.6473
Max Act: 6.6160. Min Act: -0.1700
Data Index: 301911 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19