Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.6902. Min Act: -0.1700
Data Index: 135255 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.6902. Min Act: -0.1700
Data Index: 5263965 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.5652. Min Act: -0.1700
Data Index: 743057 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.5027. Min Act: -0.1700
Data Index: 3196 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.5027. Min Act: -0.1700
Data Index: 8758285 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4715. Min Act: -0.1700
Data Index: 7951613 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4715. Min Act: -0.1700
Data Index: 2538002 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4715. Min Act: -0.1700
Data Index: 7564608 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4090. Min Act: -0.1700
Data Index: 6476012 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3777. Min Act: -0.1700
Data Index: 8620691 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.4090. Min Act: -0.1700
Data Index: 2332436 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3465. Min Act: -0.1700
Data Index: 7756602 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.3152. Min Act: -0.1700
Data Index: 293198 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2839. Min Act: -0.1700
Data Index: 5752020 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2839. Min Act: -0.1700
Data Index: 7179001 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2839. Min Act: -0.1700
Data Index: 1315736 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2839. Min Act: -0.1700
Data Index: 165830 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2527. Min Act: -0.1700
Data Index: 5383758 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2214. Min Act: -0.1700
Data Index: 8395268 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6902. Min Range: -4.6902
Max Act: 4.2527. Min Act: -0.1700
Data Index: 3959657 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19