Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3683 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.7466. Min Act: -0.1700
Data Index: 5878722 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.7154. Min Act: -0.1700
Data Index: 5310458 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.4654. Min Act: -0.1700
Data Index: 710910 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.4341. Min Act: -0.1700
Data Index: 870 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.4029. Min Act: -0.1700
Data Index: 4269679 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.3716. Min Act: -0.1700
Data Index: 7760069 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.2779. Min Act: -0.1700
Data Index: 3691205 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.3091. Min Act: -0.1700
Data Index: 6467825 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.2779. Min Act: -0.1700
Data Index: 1076239 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.2466. Min Act: -0.1700
Data Index: 2080868 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.2466. Min Act: -0.1700
Data Index: 7091222 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.2466. Min Act: -0.1700
Data Index: 1314707 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1841. Min Act: -0.1700
Data Index: 6702389 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1841. Min Act: -0.1700
Data Index: 2182547 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1529. Min Act: -0.1700
Data Index: 3740461 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1841. Min Act: -0.1700
Data Index: 2908408 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1841. Min Act: -0.1700
Data Index: 5188612 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1529. Min Act: -0.1700
Data Index: 3106829 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1529. Min Act: -0.1700
Data Index: 8476826 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7466. Min Range: -5.7466
Max Act: 5.1216. Min Act: -0.1700
Data Index: 4602450 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19