Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1601. Min Range: -6.1601
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4037646 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1601. Min Range: -6.1601
Max Act: 6.0038. Min Act: -0.1700
Data Index: 7008806 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.9101. Min Act: -0.1700
Data Index: 1059072 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.8476. Min Act: -0.1700
Data Index: 3087929 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.8163. Min Act: -0.1700
Data Index: 5473035 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.8163. Min Act: -0.1700
Data Index: 2678916 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.7851. Min Act: -0.1700
Data Index: 2678929 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.7851. Min Act: -0.1700
Data Index: 8490899 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.7538. Min Act: -0.1700
Data Index: 2678907 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.7226. Min Act: -0.1700
Data Index: 3825394 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.7226. Min Act: -0.1700
Data Index: 2678911 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.7226. Min Act: -0.1700
Data Index: 2678909 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.6601. Min Act: -0.1700
Data Index: 2678903 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.6601. Min Act: -0.1700
Data Index: 2678906 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.6913. Min Act: -0.1700
Data Index: 2678914 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.6913. Min Act: -0.1700
Data Index: 2678901 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.6288. Min Act: -0.1700
Data Index: 6159 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.5663. Min Act: -0.1700
Data Index: 2678933 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.5663. Min Act: -0.1700
Data Index: 5473034 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1601. Min Range: -6.1601
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4626085 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19