Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1332 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6914. Min Range: -6.6914
Max Act: 6.6914. Min Act: -0.1700
Data Index: 1013466 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6914. Min Range: -6.6914
Max Act: 6.5039. Min Act: -0.1700
Data Index: 282817 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6914. Min Range: -6.6914
Max Act: 6.1289. Min Act: -0.1700
Data Index: 2134012 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6914. Min Range: -6.6914
Max Act: 6.0664. Min Act: -0.1700
Data Index: 2705747 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6914. Min Range: -6.6914
Max Act: 6.0039. Min Act: -0.1700
Data Index: 169443 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6914. Min Range: -6.6914
Max Act: 6.0039. Min Act: -0.1700
Data Index: 2255336 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.9726. Min Act: -0.1700
Data Index: 866926 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.9414. Min Act: -0.1700
Data Index: 2951271 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.9726. Min Act: -0.1700
Data Index: 6748173 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.9101. Min Act: -0.1700
Data Index: 4025310 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.9101. Min Act: -0.1700
Data Index: 350543 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.9101. Min Act: -0.1700
Data Index: 1732847 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.8789. Min Act: -0.1700
Data Index: 2720172 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.9101. Min Act: -0.1700
Data Index: 8032878 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.8476. Min Act: -0.1700
Data Index: 1861719 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.8164. Min Act: -0.1700
Data Index: 8314986 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.8476. Min Act: -0.1700
Data Index: 6101252 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.8164. Min Act: -0.1700
Data Index: 5198927 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.8164. Min Act: -0.1700
Data Index: 2915691 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6914. Min Range: -6.6914
Max Act: 5.8164. Min Act: -0.1700
Data Index: 4590599 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19