Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2063. Min Range: -5.2063
Max Act: 5.2063. Min Act: -0.1700
Data Index: 1645139 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.9875. Min Act: -0.1700
Data Index: 8627089 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.9563. Min Act: -0.1700
Data Index: 3496422 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.7375. Min Act: -0.1700
Data Index: 1899048 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.7063. Min Act: -0.1700
Data Index: 3303168 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.7063. Min Act: -0.1700
Data Index: 894666 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.6750. Min Act: -0.1700
Data Index: 6772091 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.6750. Min Act: -0.1700
Data Index: 8824826 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.5813. Min Act: -0.1700
Data Index: 2300268 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.5500. Min Act: -0.1700
Data Index: 471166 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.5188. Min Act: -0.1700
Data Index: 3516541 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.4563. Min Act: -0.1700
Data Index: 8354498 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3938. Min Act: -0.1700
Data Index: 4146105 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3938. Min Act: -0.1700
Data Index: 4200302 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3938. Min Act: -0.1700
Data Index: 5102280 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3938. Min Act: -0.1700
Data Index: 735669 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3938. Min Act: -0.1700
Data Index: 8600194 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3625. Min Act: -0.1700
Data Index: 8015065 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3625. Min Act: -0.1700
Data Index: 666172 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2063. Min Range: -5.2063
Max Act: 4.3625. Min Act: -0.1700
Data Index: 8549400 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19