Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3712 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0117. Min Range: -9.0117
Max Act: 9.0117. Min Act: -0.1700
Data Index: 3057614 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0117. Min Range: -9.0117
Max Act: 9.0117. Min Act: -0.1700
Data Index: 5571715 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.9492. Min Act: -0.1700
Data Index: 2306788 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.8867. Min Act: -0.1700
Data Index: 3496815 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.8867. Min Act: -0.1700
Data Index: 3671598 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.8867. Min Act: -0.1700
Data Index: 6918621 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.8867. Min Act: -0.1700
Data Index: 1748091 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.8867. Min Act: -0.1700
Data Index: 1687364 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.8867. Min Act: -0.1700
Data Index: 1633155 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.7617. Min Act: -0.1700
Data Index: 8572198 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.8242. Min Act: -0.1700
Data Index: 444563 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.7617. Min Act: -0.1700
Data Index: 1299047 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.7617. Min Act: -0.1700
Data Index: 3435717 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.7617. Min Act: -0.1700
Data Index: 5506057 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.7617. Min Act: -0.1700
Data Index: 7394251 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.6992. Min Act: -0.1700
Data Index: 5717910 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.6367. Min Act: -0.1700
Data Index: 3313226 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.6992. Min Act: -0.1700
Data Index: 5958275 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.6992. Min Act: -0.1700
Data Index: 3068104 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0117. Min Range: -9.0117
Max Act: 8.6992. Min Act: -0.1700
Data Index: 6396345 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19