Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.5504. Min Act: -0.1700
Data Index: 7348401 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.5504. Min Act: -0.1700
Data Index: 4737888 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.5192. Min Act: -0.1700
Data Index: 4779106 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.5192. Min Act: -0.1700
Data Index: 4991398 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.4567. Min Act: -0.1700
Data Index: 8829236 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.4254. Min Act: -0.1700
Data Index: 1678844 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.4879. Min Act: -0.1700
Data Index: 4321462 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3942. Min Act: -0.1700
Data Index: 2449311 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3317. Min Act: -0.1700
Data Index: 8207065 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3317. Min Act: -0.1700
Data Index: 1912425 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3629. Min Act: -0.1700
Data Index: 5286649 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3629. Min Act: -0.1700
Data Index: 7203702 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3317. Min Act: -0.1700
Data Index: 1551153 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3004. Min Act: -0.1700
Data Index: 3004822 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.2692. Min Act: -0.1700
Data Index: 4010726 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3004. Min Act: -0.1700
Data Index: 2742127 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3004. Min Act: -0.1700
Data Index: 4987764 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3004. Min Act: -0.1700
Data Index: 2565331 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.2692. Min Act: -0.1700
Data Index: 5255910 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5504. Min Range: -6.5504
Max Act: 6.3004. Min Act: -0.1700
Data Index: 6970110 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19