Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1062 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.9863. Min Act: -0.1700
Data Index: 895964 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.9550. Min Act: -0.1700
Data Index: 6484584 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.7675. Min Act: -0.1700
Data Index: 6614628 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.7675. Min Act: -0.1700
Data Index: 2966391 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.7050. Min Act: -0.1700
Data Index: 1293016 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.6425. Min Act: -0.1700
Data Index: 4284022 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.6425. Min Act: -0.1700
Data Index: 6079760 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.6425. Min Act: -0.1700
Data Index: 2535668 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5800. Min Act: -0.1700
Data Index: 2168134 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5800. Min Act: -0.1700
Data Index: 6068996 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5488. Min Act: -0.1700
Data Index: 503349 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.6113. Min Act: -0.1700
Data Index: 7244480 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5488. Min Act: -0.1700
Data Index: 8422712 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5800. Min Act: -0.1700
Data Index: 3540062 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5488. Min Act: -0.1700
Data Index: 1702461 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5488. Min Act: -0.1700
Data Index: 3120893 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5488. Min Act: -0.1700
Data Index: 1064803 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.5175. Min Act: -0.1700
Data Index: 687972 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.4863. Min Act: -0.1700
Data Index: 5550922 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9863. Min Range: -6.9863
Max Act: 6.4550. Min Act: -0.1700
Data Index: 8163174 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19