Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5184 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.9598. Min Act: -0.1700
Data Index: 3649599 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.9598. Min Act: -0.1700
Data Index: 5686338 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.9598. Min Act: -0.1700
Data Index: 8230850 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.9285. Min Act: -0.1700
Data Index: 3583144 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.9285. Min Act: -0.1700
Data Index: 5709399 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.9285. Min Act: -0.1700
Data Index: 7187315 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8660. Min Act: -0.1700
Data Index: 4628694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8660. Min Act: -0.1700
Data Index: 5365170 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8660. Min Act: -0.1700
Data Index: 7528681 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8660. Min Act: -0.1700
Data Index: 7357400 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8660. Min Act: -0.1700
Data Index: 4738680 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8660. Min Act: -0.1700
Data Index: 682139 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8347. Min Act: -0.1700
Data Index: 5225385 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8347. Min Act: -0.1700
Data Index: 3223136 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8347. Min Act: -0.1700
Data Index: 6773481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8347. Min Act: -0.1700
Data Index: 4699110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8347. Min Act: -0.1700
Data Index: 844748 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8035. Min Act: -0.1700
Data Index: 420107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8035. Min Act: -0.1700
Data Index: 2159860 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9598. Min Range: -3.9598
Max Act: 3.8035. Min Act: -0.1700
Data Index: 4072724 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19