Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4800 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3876. Min Range: -6.3876
Max Act: 6.3876. Min Act: -0.1700
Data Index: 8239448 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3876. Min Range: -6.3876
Max Act: 6.2938. Min Act: -0.1700
Data Index: 1496013 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3876. Min Range: -6.3876
Max Act: 6.2626. Min Act: -0.1700
Data Index: 5483120 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3876. Min Range: -6.3876
Max Act: 6.1376. Min Act: -0.1700
Data Index: 1655675 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3876. Min Range: -6.3876
Max Act: 6.0751. Min Act: -0.1700
Data Index: 6376651 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.9813. Min Act: -0.1700
Data Index: 1657737 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.9813. Min Act: -0.1700
Data Index: 8465150 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.9813. Min Act: -0.1700
Data Index: 6907818 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.9501. Min Act: -0.1700
Data Index: 3851277 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.9188. Min Act: -0.1700
Data Index: 8351474 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.9188. Min Act: -0.1700
Data Index: 3902649 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.9188. Min Act: -0.1700
Data Index: 4396908 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8876. Min Act: -0.1700
Data Index: 1888545 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8563. Min Act: -0.1700
Data Index: 8585289 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8251. Min Act: -0.1700
Data Index: 7151015 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8251. Min Act: -0.1700
Data Index: 1888548 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8251. Min Act: -0.1700
Data Index: 4176380 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8251. Min Act: -0.1700
Data Index: 674135 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8251. Min Act: -0.1700
Data Index: 6325063 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3876. Min Range: -6.3876
Max Act: 5.8251. Min Act: -0.1700
Data Index: 4954231 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19