Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6237 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0924. Min Range: -6.0924
Max Act: 6.0924. Min Act: -0.1700
Data Index: 907130 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.5611. Min Act: -0.1700
Data Index: 3182945 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.5299. Min Act: -0.1700
Data Index: 5553978 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4986. Min Act: -0.1700
Data Index: 7721371 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4986. Min Act: -0.1700
Data Index: 1433274 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4986. Min Act: -0.1700
Data Index: 6742732 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4674. Min Act: -0.1700
Data Index: 2229627 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4361. Min Act: -0.1700
Data Index: 3525413 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4049. Min Act: -0.1700
Data Index: 5259858 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4049. Min Act: -0.1700
Data Index: 1490012 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.4049. Min Act: -0.1700
Data Index: 3145492 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3736. Min Act: -0.1700
Data Index: 849971 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3736. Min Act: -0.1700
Data Index: 4840887 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3424. Min Act: -0.1700
Data Index: 3140723 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3424. Min Act: -0.1700
Data Index: 967186 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3424. Min Act: -0.1700
Data Index: 5685307 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3424. Min Act: -0.1700
Data Index: 207555 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3424. Min Act: -0.1700
Data Index: 6179874 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3424. Min Act: -0.1700
Data Index: 3393840 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.3424. Min Act: -0.1700
Data Index: 872762 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19