Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.5667. Min Act: -0.1700
Data Index: 4465481 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.5667. Min Act: -0.1700
Data Index: 4028798 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.5042. Min Act: -0.1700
Data Index: 5820802 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.4417. Min Act: -0.1700
Data Index: 5679164 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.3792. Min Act: -0.1700
Data Index: 5740690 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.3167. Min Act: -0.1700
Data Index: 5710596 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.3167. Min Act: -0.1700
Data Index: 5740687 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.3167. Min Act: -0.1700
Data Index: 2492691 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.1917. Min Act: -0.1700
Data Index: 5740696 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.1292. Min Act: -0.1700
Data Index: 8618729 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.1292. Min Act: -0.1700
Data Index: 8148872 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.1292. Min Act: -0.1700
Data Index: 5740695 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.0667. Min Act: -0.1700
Data Index: 5740686 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.0042. Min Act: -0.1700
Data Index: 189968 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5667. Min Range: -10.5667
Max Act: 10.0042. Min Act: -0.1700
Data Index: 5026546 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5667. Min Range: -10.5667
Max Act: 9.9417. Min Act: -0.1700
Data Index: 7514937 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5667. Min Range: -10.5667
Max Act: 9.8792. Min Act: -0.1700
Data Index: 1774898 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5667. Min Range: -10.5667
Max Act: 9.9417. Min Act: -0.1700
Data Index: 299724 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5667. Min Range: -10.5667
Max Act: 9.9417. Min Act: -0.1700
Data Index: 291816 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5667. Min Range: -10.5667
Max Act: 9.9417. Min Act: -0.1700
Data Index: 7269031 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19