Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.7182. Min Act: -0.1700
Data Index: 4472516 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.5932. Min Act: -0.1700
Data Index: 4902122 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.5620. Min Act: -0.1700
Data Index: 8667369 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.4370. Min Act: -0.1700
Data Index: 1349042 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3745. Min Act: -0.1700
Data Index: 1349041 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3745. Min Act: -0.1700
Data Index: 475582 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3745. Min Act: -0.1700
Data Index: 3930684 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3432. Min Act: -0.1700
Data Index: 661051 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3432. Min Act: -0.1700
Data Index: 8461950 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3432. Min Act: -0.1700
Data Index: 5326717 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7763459 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3120. Min Act: -0.1700
Data Index: 4506090 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3432. Min Act: -0.1700
Data Index: 762732 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2304637 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3120. Min Act: -0.1700
Data Index: 8558115 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.2807. Min Act: -0.1700
Data Index: 1566764 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.2807. Min Act: -0.1700
Data Index: 6829893 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3120. Min Act: -0.1700
Data Index: 3422509 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.2807. Min Act: -0.1700
Data Index: 1709088 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7182. Min Range: -5.7182
Max Act: 5.3120. Min Act: -0.1700
Data Index: 3328171 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19