Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4737 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.9290. Min Act: -0.1700
Data Index: 79896 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.8978. Min Act: -0.1700
Data Index: 6814551 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.8040. Min Act: -0.1700
Data Index: 79898 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.7415. Min Act: -0.1700
Data Index: 1227204 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.7728. Min Act: -0.1700
Data Index: 4373217 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.7728. Min Act: -0.1700
Data Index: 8613921 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.7103. Min Act: -0.1700
Data Index: 1975077 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.6790. Min Act: -0.1700
Data Index: 7532934 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.6478. Min Act: -0.1700
Data Index: 420286 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.6165. Min Act: -0.1700
Data Index: 5774906 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.5853. Min Act: -0.1700
Data Index: 1724687 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.5853. Min Act: -0.1700
Data Index: 5672164 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.5853. Min Act: -0.1700
Data Index: 4472841 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.5853. Min Act: -0.1700
Data Index: 5415473 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.5540. Min Act: -0.1700
Data Index: 7436697 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.5540. Min Act: -0.1700
Data Index: 2681102 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 8558655 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.4603. Min Act: -0.1700
Data Index: 621351 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.4603. Min Act: -0.1700
Data Index: 7207358 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9290. Min Range: -4.9290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 663144 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19