Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1046 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.6126. Min Act: -0.1700
Data Index: 8214592 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.3938. Min Act: -0.1700
Data Index: 3516403 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.2688. Min Act: -0.1700
Data Index: 847677 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.3001. Min Act: -0.1700
Data Index: 2493735 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.1751. Min Act: -0.1700
Data Index: 4812487 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.1438. Min Act: -0.1700
Data Index: 2796017 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.1126. Min Act: -0.1700
Data Index: 6923516 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.1438. Min Act: -0.1700
Data Index: 847672 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.1126. Min Act: -0.1700
Data Index: 4232606 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.1126. Min Act: -0.1700
Data Index: 587755 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.0813. Min Act: -0.1700
Data Index: 5319896 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.0501. Min Act: -0.1700
Data Index: 4052491 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.0188. Min Act: -0.1700
Data Index: 1892107 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6126. Min Range: -5.6126
Max Act: 4.9876. Min Act: -0.1700
Data Index: 3485381 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.0188. Min Act: -0.1700
Data Index: 908533 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.0188. Min Act: -0.1700
Data Index: 5567222 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6126. Min Range: -5.6126
Max Act: 5.0188. Min Act: -0.1700
Data Index: 4085205 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6126. Min Range: -5.6126
Max Act: 4.9563. Min Act: -0.1700
Data Index: 1634836 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6126. Min Range: -5.6126
Max Act: 4.9876. Min Act: -0.1700
Data Index: 327647 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6126. Min Range: -5.6126
Max Act: 4.9563. Min Act: -0.1700
Data Index: 2803735 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19