Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.4097. Min Act: -0.1700
Data Index: 8420067 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.3472. Min Act: -0.1700
Data Index: 3049432 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.3472. Min Act: -0.1700
Data Index: 3834588 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.2847. Min Act: -0.1700
Data Index: 8669203 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.2847. Min Act: -0.1700
Data Index: 5408388 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.2222. Min Act: -0.1700
Data Index: 4839643 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.0972. Min Act: -0.1700
Data Index: 8029303 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.0035. Min Act: -0.1700
Data Index: 2066743 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.9722. Min Act: -0.1700
Data Index: 6174913 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.0035. Min Act: -0.1700
Data Index: 455992 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.9410. Min Act: -0.1700
Data Index: 1999514 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.9410. Min Act: -0.1700
Data Index: 5944237 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.9097. Min Act: -0.1700
Data Index: 8029302 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.9097. Min Act: -0.1700
Data Index: 8095435 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8785. Min Act: -0.1700
Data Index: 2105062 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8472. Min Act: -0.1700
Data Index: 3854774 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8472. Min Act: -0.1700
Data Index: 5067611 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8472. Min Act: -0.1700
Data Index: 435523 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8472. Min Act: -0.1700
Data Index: 5421711 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8472. Min Act: -0.1700
Data Index: 1176945 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19