Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.5660. Min Act: -0.1700
Data Index: 7220643 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.2535. Min Act: -0.1700
Data Index: 2164897 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.2535. Min Act: -0.1700
Data Index: 1204880 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.1910. Min Act: -0.1700
Data Index: 6441629 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.1597. Min Act: -0.1700
Data Index: 733757 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.1285. Min Act: -0.1700
Data Index: 3090042 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.1285. Min Act: -0.1700
Data Index: 2341781 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0660. Min Act: -0.1700
Data Index: 8490303 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0347. Min Act: -0.1700
Data Index: 3509049 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0035. Min Act: -0.1700
Data Index: 3589264 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0347. Min Act: -0.1700
Data Index: 2668737 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0035. Min Act: -0.1700
Data Index: 2004847 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0035. Min Act: -0.1700
Data Index: 7334286 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0035. Min Act: -0.1700
Data Index: 6540720 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0035. Min Act: -0.1700
Data Index: 820758 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5660. Min Range: -6.5660
Max Act: 5.9722. Min Act: -0.1700
Data Index: 6434305 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5660. Min Range: -6.5660
Max Act: 6.0035. Min Act: -0.1700
Data Index: 5925557 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5660. Min Range: -6.5660
Max Act: 5.9722. Min Act: -0.1700
Data Index: 8118972 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5660. Min Range: -6.5660
Max Act: 5.9410. Min Act: -0.1700
Data Index: 4853876 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5660. Min Range: -6.5660
Max Act: 5.9097. Min Act: -0.1700
Data Index: 946721 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19