Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3569 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1434. Min Range: -7.1434
Max Act: 7.1434. Min Act: -0.1700
Data Index: 4673732 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1434. Min Range: -7.1434
Max Act: 7.1122. Min Act: -0.1700
Data Index: 8549774 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.9247. Min Act: -0.1700
Data Index: 4931378 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.8622. Min Act: -0.1700
Data Index: 337130 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.7997. Min Act: -0.1700
Data Index: 2785338 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.7684. Min Act: -0.1700
Data Index: 4965974 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.7372. Min Act: -0.1700
Data Index: 1277844 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.7059. Min Act: -0.1700
Data Index: 1993655 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6747. Min Act: -0.1700
Data Index: 2212279 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6434. Min Act: -0.1700
Data Index: 5623083 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6434. Min Act: -0.1700
Data Index: 8656979 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6434. Min Act: -0.1700
Data Index: 6559868 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6434. Min Act: -0.1700
Data Index: 5982902 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6122. Min Act: -0.1700
Data Index: 6565928 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6122. Min Act: -0.1700
Data Index: 2997521 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6434. Min Act: -0.1700
Data Index: 2870649 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6122. Min Act: -0.1700
Data Index: 3698700 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.6122. Min Act: -0.1700
Data Index: 7152516 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.5809. Min Act: -0.1700
Data Index: 4335688 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1434. Min Range: -7.1434
Max Act: 6.5809. Min Act: -0.1700
Data Index: 5845321 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19