Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4659 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.2851. Min Act: -0.1700
Data Index: 4229999 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.9542. Min Act: -0.1700
Data Index: 1056057 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.9542. Min Act: -0.1700
Data Index: 4230000 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.9225. Min Act: -0.1700
Data Index: 813430 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.9225. Min Act: -0.1700
Data Index: 6297138 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.8908. Min Act: -0.1700
Data Index: 7222220 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.8591. Min Act: -0.1700
Data Index: 1516949 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.8908. Min Act: -0.1700
Data Index: 5353313 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.8591. Min Act: -0.1700
Data Index: 1191908 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.8591. Min Act: -0.1700
Data Index: 1576327 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.8114. Min Act: -0.1700
Data Index: 7222219 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.8273. Min Act: -0.1700
Data Index: 1191910 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7955. Min Act: -0.1700
Data Index: 7100616 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7795. Min Act: -0.1700
Data Index: 2049725 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7795. Min Act: -0.1700
Data Index: 8476399 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7636. Min Act: -0.1700
Data Index: 5040627 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7476. Min Act: -0.1700
Data Index: 1191928 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7316. Min Act: -0.1700
Data Index: 5631923 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7476. Min Act: -0.1700
Data Index: 5199856 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2851. Min Range: -3.2851
Max Act: 2.7157. Min Act: -0.1700
Data Index: 3035768 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19