Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1015 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2877. Min Act: -0.1700
Data Index: 1281664 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2877. Min Act: -0.1700
Data Index: 5426140 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2877. Min Act: -0.1700
Data Index: 1172206 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2877. Min Act: -0.1700
Data Index: 2766583 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2877. Min Act: -0.1700
Data Index: 4566507 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 5158694 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 11689 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 4620936 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 2212808 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 186304 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 1620030 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 3750374 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 6803517 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2877. Min Act: -0.1700
Data Index: 5880483 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2564. Min Act: -0.1700
Data Index: 369535 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2252. Min Act: -0.1700
Data Index: 4012043 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2252. Min Act: -0.1700
Data Index: 4435566 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2252. Min Act: -0.1700
Data Index: 2748906 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2252. Min Act: -0.1700
Data Index: 2671255 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2877. Min Range: -4.2877
Max Act: 4.2252. Min Act: -0.1700
Data Index: 1773158 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19