Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 662 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1910. Min Range: -7.1910
Max Act: 7.1910. Min Act: -0.1700
Data Index: 6652940 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1910. Min Range: -7.1910
Max Act: 7.1910. Min Act: -0.1700
Data Index: 5234316 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1910. Min Range: -7.1910
Max Act: 7.1598. Min Act: -0.1700
Data Index: 8569535 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1910. Min Range: -7.1910
Max Act: 7.0660. Min Act: -0.1700
Data Index: 3645932 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1910. Min Range: -7.1910
Max Act: 7.0348. Min Act: -0.1700
Data Index: 3865633 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1910. Min Range: -7.1910
Max Act: 7.0035. Min Act: -0.1700
Data Index: 7656342 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1910. Min Range: -7.1910
Max Act: 7.0035. Min Act: -0.1700
Data Index: 6989014 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.9410. Min Act: -0.1700
Data Index: 4430070 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.9723. Min Act: -0.1700
Data Index: 512117 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.9410. Min Act: -0.1700
Data Index: 5084759 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.9098. Min Act: -0.1700
Data Index: 6984134 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.8785. Min Act: -0.1700
Data Index: 7310215 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.8473. Min Act: -0.1700
Data Index: 4513313 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.8473. Min Act: -0.1700
Data Index: 1500727 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.8160. Min Act: -0.1700
Data Index: 285945 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.8473. Min Act: -0.1700
Data Index: 8818074 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.8160. Min Act: -0.1700
Data Index: 4973241 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.7848. Min Act: -0.1700
Data Index: 4377426 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.7848. Min Act: -0.1700
Data Index: 3473968 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1910. Min Range: -7.1910
Max Act: 6.7848. Min Act: -0.1700
Data Index: 5254498 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19