Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5472 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.6368. Min Act: -0.1700
Data Index: 7987173 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.6368. Min Act: -0.1700
Data Index: 1647788 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.5844. Min Act: -0.1700
Data Index: 7794812 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.5844. Min Act: -0.1700
Data Index: 1438535 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.5319. Min Act: -0.1700
Data Index: 1257925 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.5319. Min Act: -0.1700
Data Index: 315179 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.5319. Min Act: -0.1700
Data Index: 6671454 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4968. Min Act: -0.1700
Data Index: 564988 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.5143. Min Act: -0.1700
Data Index: 5014062 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4968. Min Act: -0.1700
Data Index: 1246419 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4968. Min Act: -0.1700
Data Index: 6157882 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4968. Min Act: -0.1700
Data Index: 4131092 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4792. Min Act: -0.1700
Data Index: 2828481 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4792. Min Act: -0.1700
Data Index: 5164498 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4792. Min Act: -0.1700
Data Index: 4142241 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4792. Min Act: -0.1700
Data Index: 5864932 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4616. Min Act: -0.1700
Data Index: 6038435 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4616. Min Act: -0.1700
Data Index: 1087966 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4616. Min Act: -0.1700
Data Index: 6907826 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6368. Min Range: -1.6368
Max Act: 1.4616. Min Act: -0.1700
Data Index: 988921 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19