Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2926. Min Range: -3.2926
Max Act: 3.2926. Min Act: -0.1700
Data Index: 4489778 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2926. Min Range: -3.2926
Max Act: 3.1039. Min Act: -0.1700
Data Index: 2699380 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2926. Min Range: -3.2926
Max Act: 3.0566. Min Act: -0.1700
Data Index: 7528344 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2926. Min Range: -3.2926
Max Act: 3.0250. Min Act: -0.1700
Data Index: 8582843 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2926. Min Range: -3.2926
Max Act: 3.0250. Min Act: -0.1700
Data Index: 7419015 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2926. Min Range: -3.2926
Max Act: 3.0250. Min Act: -0.1700
Data Index: 6783470 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2926. Min Range: -3.2926
Max Act: 3.0092. Min Act: -0.1700
Data Index: 2292594 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9934. Min Act: -0.1700
Data Index: 7712069 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9776. Min Act: -0.1700
Data Index: 8365940 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9776. Min Act: -0.1700
Data Index: 144078 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9618. Min Act: -0.1700
Data Index: 8383352 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9301. Min Act: -0.1700
Data Index: 489114 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9459. Min Act: -0.1700
Data Index: 8292862 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9301. Min Act: -0.1700
Data Index: 6164576 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9459. Min Act: -0.1700
Data Index: 5308585 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9301. Min Act: -0.1700
Data Index: 1406259 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9142. Min Act: -0.1700
Data Index: 7331089 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9301. Min Act: -0.1700
Data Index: 1780840 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.9142. Min Act: -0.1700
Data Index: 5158482 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2926. Min Range: -3.2926
Max Act: 2.8984. Min Act: -0.1700
Data Index: 3216804 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19