Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.2788. Min Act: -0.1700
Data Index: 3596002 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.1538. Min Act: -0.1700
Data Index: 6383301 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.1538. Min Act: -0.1700
Data Index: 1412058 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.1538. Min Act: -0.1700
Data Index: 1717977 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.1226. Min Act: -0.1700
Data Index: 8245890 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.1226. Min Act: -0.1700
Data Index: 1956187 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.1226. Min Act: -0.1700
Data Index: 271588 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.0601. Min Act: -0.1700
Data Index: 7668962 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.0601. Min Act: -0.1700
Data Index: 111831 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.0601. Min Act: -0.1700
Data Index: 7448115 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9976. Min Act: -0.1700
Data Index: 5470812 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2788. Min Range: -6.2788
Max Act: 6.0288. Min Act: -0.1700
Data Index: 6383304 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9976. Min Act: -0.1700
Data Index: 5013198 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9663. Min Act: -0.1700
Data Index: 3992705 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9038. Min Act: -0.1700
Data Index: 5587990 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9038. Min Act: -0.1700
Data Index: 3519798 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9038. Min Act: -0.1700
Data Index: 7788370 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9038. Min Act: -0.1700
Data Index: 6383303 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.9038. Min Act: -0.1700
Data Index: 4245724 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2788. Min Range: -6.2788
Max Act: 5.8413. Min Act: -0.1700
Data Index: 6208156 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19