Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.4826. Min Act: -0.1700
Data Index: 1770678 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.3576. Min Act: -0.1700
Data Index: 3004271 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.3889. Min Act: -0.1700
Data Index: 166086 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.3576. Min Act: -0.1700
Data Index: 5295837 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.2951. Min Act: -0.1700
Data Index: 6873241 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.2639. Min Act: -0.1700
Data Index: 484003 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.2951. Min Act: -0.1700
Data Index: 2755243 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.2014. Min Act: -0.1700
Data Index: 6097307 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.1701. Min Act: -0.1700
Data Index: 912057 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.1389. Min Act: -0.1700
Data Index: 958955 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.1076. Min Act: -0.1700
Data Index: 7096772 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.1076. Min Act: -0.1700
Data Index: 8412116 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.1076. Min Act: -0.1700
Data Index: 4312661 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.1389. Min Act: -0.1700
Data Index: 7863403 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.1076. Min Act: -0.1700
Data Index: 3407673 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0764. Min Act: -0.1700
Data Index: 295759 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0451. Min Act: -0.1700
Data Index: 7179605 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0451. Min Act: -0.1700
Data Index: 7856533 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0451. Min Act: -0.1700
Data Index: 2977886 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.9826. Min Act: -0.1700
Data Index: 5257015 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19