Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.6849. Min Act: -0.1700
Data Index: 6354818 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.4037. Min Act: -0.1700
Data Index: 602901 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.3724. Min Act: -0.1700
Data Index: 8649339 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.3412. Min Act: -0.1700
Data Index: 2894167 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.2787. Min Act: -0.1700
Data Index: 2862883 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.2787. Min Act: -0.1700
Data Index: 1554826 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.2162. Min Act: -0.1700
Data Index: 8408149 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.2162. Min Act: -0.1700
Data Index: 5453833 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1849. Min Act: -0.1700
Data Index: 1539945 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.2162. Min Act: -0.1700
Data Index: 5689183 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1849. Min Act: -0.1700
Data Index: 6815880 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1537. Min Act: -0.1700
Data Index: 600309 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1537. Min Act: -0.1700
Data Index: 2726524 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1537. Min Act: -0.1700
Data Index: 2953001 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1537. Min Act: -0.1700
Data Index: 1039352 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1224. Min Act: -0.1700
Data Index: 3209322 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1224. Min Act: -0.1700
Data Index: 6137016 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1224. Min Act: -0.1700
Data Index: 3793060 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1224. Min Act: -0.1700
Data Index: 6674085 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6849. Min Range: -5.6849
Max Act: 5.1224. Min Act: -0.1700
Data Index: 5353945 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19