Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1498 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.5134. Min Act: -0.1700
Data Index: 8778300 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.4821. Min Act: -0.1700
Data Index: 5427083 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.4821. Min Act: -0.1700
Data Index: 7759260 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.4509. Min Act: -0.1700
Data Index: 8625486 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 4238384 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 7996373 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.2634. Min Act: -0.1700
Data Index: 303585 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.2009. Min Act: -0.1700
Data Index: 7475687 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.2009. Min Act: -0.1700
Data Index: 3839523 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 865411 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 6700415 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 8303287 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 3872576 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 7644853 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 4960392 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1384. Min Act: -0.1700
Data Index: 4784546 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1384. Min Act: -0.1700
Data Index: 126667 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1384. Min Act: -0.1700
Data Index: 1830614 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 4134062 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1071. Min Act: -0.1700
Data Index: 1663774 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19