Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7638. Min Range: -8.7638
Max Act: 8.7638. Min Act: -0.1700
Data Index: 5794301 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7638. Min Range: -8.7638
Max Act: 8.2638. Min Act: -0.1700
Data Index: 8124867 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7638. Min Range: -8.7638
Max Act: 8.1388. Min Act: -0.1700
Data Index: 3957753 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7638. Min Range: -8.7638
Max Act: 8.1388. Min Act: -0.1700
Data Index: 8416181 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.9513. Min Act: -0.1700
Data Index: 3189526 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7638. Min Act: -0.1700
Data Index: 4292155 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7951. Min Act: -0.1700
Data Index: 2149872 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7638. Min Act: -0.1700
Data Index: 5819011 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7638. Min Act: -0.1700
Data Index: 2672703 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7638. Min Act: -0.1700
Data Index: 3476740 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7326. Min Act: -0.1700
Data Index: 8647822 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7326. Min Act: -0.1700
Data Index: 6728437 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7326. Min Act: -0.1700
Data Index: 8537738 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7013. Min Act: -0.1700
Data Index: 3121196 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7013. Min Act: -0.1700
Data Index: 2576600 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.7013. Min Act: -0.1700
Data Index: 4673413 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.6701. Min Act: -0.1700
Data Index: 7519914 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.6701. Min Act: -0.1700
Data Index: 4170743 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.5763. Min Act: -0.1700
Data Index: 7850922 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7638. Min Range: -8.7638
Max Act: 7.6076. Min Act: -0.1700
Data Index: 2086941 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19