Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1847 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2410. Min Range: -9.2410
Max Act: 9.2410. Min Act: -0.1700
Data Index: 6536500 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2410. Min Range: -9.2410
Max Act: 9.1785. Min Act: -0.1700
Data Index: 3868352 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2410. Min Range: -9.2410
Max Act: 9.1785. Min Act: -0.1700
Data Index: 8163332 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.9910. Min Act: -0.1700
Data Index: 675981 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.8035. Min Act: -0.1700
Data Index: 3996183 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.7410. Min Act: -0.1700
Data Index: 8821035 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6785. Min Act: -0.1700
Data Index: 3881999 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6785. Min Act: -0.1700
Data Index: 8560804 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6160. Min Act: -0.1700
Data Index: 4047439 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.7410. Min Act: -0.1700
Data Index: 2084145 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6160. Min Act: -0.1700
Data Index: 4403543 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6160. Min Act: -0.1700
Data Index: 3513633 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6160. Min Act: -0.1700
Data Index: 1783907 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6160. Min Act: -0.1700
Data Index: 377675 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.6160. Min Act: -0.1700
Data Index: 6733086 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.5535. Min Act: -0.1700
Data Index: 3182844 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.5535. Min Act: -0.1700
Data Index: 8560812 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.5535. Min Act: -0.1700
Data Index: 1268484 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.5535. Min Act: -0.1700
Data Index: 8821051 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2410. Min Range: -9.2410
Max Act: 8.5535. Min Act: -0.1700
Data Index: 2646620 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19