Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.6182. Min Act: -0.1700
Data Index: 6594741 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.5555. Min Act: -0.1700
Data Index: 5653960 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.5242. Min Act: -0.1700
Data Index: 5953886 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4929. Min Act: -0.1700
Data Index: 4084358 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4616. Min Act: -0.1700
Data Index: 6754055 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4616. Min Act: -0.1700
Data Index: 5281839 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4616. Min Act: -0.1700
Data Index: 122942 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4616. Min Act: -0.1700
Data Index: 128369 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4302. Min Act: -0.1700
Data Index: 2932073 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4302. Min Act: -0.1700
Data Index: 7876183 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4302. Min Act: -0.1700
Data Index: 8620696 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4302. Min Act: -0.1700
Data Index: 5198132 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.4302. Min Act: -0.1700
Data Index: 6282706 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.3989. Min Act: -0.1700
Data Index: 6642063 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.3989. Min Act: -0.1700
Data Index: 2345091 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.3989. Min Act: -0.1700
Data Index: 3723222 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.3989. Min Act: -0.1700
Data Index: 5709367 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.3989. Min Act: -0.1700
Data Index: 3453412 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.3989. Min Act: -0.1700
Data Index: 5439576 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6182. Min Range: -3.6182
Max Act: 3.3989. Min Act: -0.1700
Data Index: 3246385 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19