Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.9413. Min Act: -0.1700
Data Index: 8424475 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.9100. Min Act: -0.1700
Data Index: 420365 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.8788. Min Act: -0.1700
Data Index: 8659808 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.8163. Min Act: -0.1700
Data Index: 5490789 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6360907 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6969668 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.7538. Min Act: -0.1700
Data Index: 8054943 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.8163. Min Act: -0.1700
Data Index: 300282 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.7538. Min Act: -0.1700
Data Index: 6809163 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.7538. Min Act: -0.1700
Data Index: 8799719 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6913. Min Act: -0.1700
Data Index: 3432164 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6913. Min Act: -0.1700
Data Index: 739934 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6600. Min Act: -0.1700
Data Index: 5359422 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6600. Min Act: -0.1700
Data Index: 6263655 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6600. Min Act: -0.1700
Data Index: 3662497 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6600. Min Act: -0.1700
Data Index: 5619693 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6288. Min Act: -0.1700
Data Index: 7316559 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6288. Min Act: -0.1700
Data Index: 7652915 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.6600. Min Act: -0.1700
Data Index: 8314388 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9413. Min Range: -5.9413
Max Act: 5.5975. Min Act: -0.1700
Data Index: 1148105 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19