Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3410. Min Range: -6.3410
Max Act: 6.3410. Min Act: -0.1700
Data Index: 8227470 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.9973. Min Act: -0.1700
Data Index: 3284280 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8723. Min Act: -0.1700
Data Index: 1984702 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8410. Min Act: -0.1700
Data Index: 402210 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8410. Min Act: -0.1700
Data Index: 3255591 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8410. Min Act: -0.1700
Data Index: 2236517 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8410. Min Act: -0.1700
Data Index: 3236192 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8098. Min Act: -0.1700
Data Index: 2494170 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8098. Min Act: -0.1700
Data Index: 1244199 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8098. Min Act: -0.1700
Data Index: 6661167 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.8098. Min Act: -0.1700
Data Index: 3250314 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7785. Min Act: -0.1700
Data Index: 2694742 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7785. Min Act: -0.1700
Data Index: 2150540 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7160. Min Act: -0.1700
Data Index: 3986586 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7785. Min Act: -0.1700
Data Index: 5607954 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7160. Min Act: -0.1700
Data Index: 4296349 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.6848. Min Act: -0.1700
Data Index: 3783943 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7160. Min Act: -0.1700
Data Index: 107371 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7160. Min Act: -0.1700
Data Index: 4940244 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3410. Min Range: -6.3410
Max Act: 5.7160. Min Act: -0.1700
Data Index: 3116153 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19