Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0090. Min Range: -6.0090
Max Act: 6.0090. Min Act: -0.1700
Data Index: 5658115 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.6965. Min Act: -0.1700
Data Index: 7306017 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.5090. Min Act: -0.1700
Data Index: 3465427 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.5090. Min Act: -0.1700
Data Index: 2580981 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.4465. Min Act: -0.1700
Data Index: 480686 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.4465. Min Act: -0.1700
Data Index: 3800845 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.4465. Min Act: -0.1700
Data Index: 8075959 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.4152. Min Act: -0.1700
Data Index: 4872553 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3840. Min Act: -0.1700
Data Index: 3079729 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3840. Min Act: -0.1700
Data Index: 3722870 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3840. Min Act: -0.1700
Data Index: 2421741 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3527. Min Act: -0.1700
Data Index: 5137229 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3527. Min Act: -0.1700
Data Index: 3509579 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3840. Min Act: -0.1700
Data Index: 6106855 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3215. Min Act: -0.1700
Data Index: 7751859 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3215. Min Act: -0.1700
Data Index: 7013710 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.3215. Min Act: -0.1700
Data Index: 8267895 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.2902. Min Act: -0.1700
Data Index: 1368553 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.2902. Min Act: -0.1700
Data Index: 4205826 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0090. Min Range: -6.0090
Max Act: 5.2590. Min Act: -0.1700
Data Index: 3249314 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19