Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5658 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.8101. Min Act: -0.1700
Data Index: 6040126 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6226. Min Act: -0.1700
Data Index: 4176038 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7047426 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5601. Min Act: -0.1700
Data Index: 6572349 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5601. Min Act: -0.1700
Data Index: 7871630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.5601. Min Act: -0.1700
Data Index: 1824514 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 6311951 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 6036959 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 2158208 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 4992434 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1677
Data Index: 387296 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 8064841 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1699
Data Index: 4541929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 7416884 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4976. Min Act: -0.1700
Data Index: 6291286 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4351. Min Act: -0.1700
Data Index: 770308 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4351. Min Act: -0.1700
Data Index: 5488764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4351. Min Act: -0.1700
Data Index: 2780519 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4351. Min Act: -0.1700
Data Index: 800778 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8101. Min Range: -6.8101
Max Act: 6.4351. Min Act: -0.1700
Data Index: 6040140 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19