Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2195 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.4097. Min Act: -0.1700
Data Index: 179569 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.2999. Min Act: -0.1700
Data Index: 6642155 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.2685. Min Act: -0.1700
Data Index: 6246350 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.2371. Min Act: -0.1700
Data Index: 1244647 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.2057. Min Act: -0.1700
Data Index: 7907931 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.2057. Min Act: -0.1700
Data Index: 6576726 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1899. Min Act: -0.1700
Data Index: 31885 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1742. Min Act: -0.1700
Data Index: 959657 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1899. Min Act: -0.1700
Data Index: 8383575 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1427. Min Act: -0.1700
Data Index: 7142864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1270. Min Act: -0.1700
Data Index: 4503406 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1427. Min Act: -0.1700
Data Index: 630136 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1270. Min Act: -0.1698
Data Index: 1362249 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.1112. Min Act: -0.1700
Data Index: 5878533 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.0797. Min Act: -0.1700
Data Index: 7850045 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.0639. Min Act: -0.1700
Data Index: 7958441 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.0639. Min Act: -0.1699
Data Index: 6252290 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.0639. Min Act: -0.1700
Data Index: 6331528 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.0639. Min Act: -0.1700
Data Index: 7407074 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4097. Min Range: -3.4097
Max Act: 3.0639. Min Act: -0.1700
Data Index: 8355327 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19