Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.9648. Min Act: -0.1700
Data Index: 8785708 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.8711. Min Act: -0.1700
Data Index: 2632308 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.8086. Min Act: -0.1700
Data Index: 1857078 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.7773. Min Act: -0.1700
Data Index: 7490232 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.7148. Min Act: -0.1700
Data Index: 5785400 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.6523. Min Act: -0.1700
Data Index: 7671090 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.6836. Min Act: -0.1700
Data Index: 4966649 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.6523. Min Act: -0.1700
Data Index: 7176827 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.6211. Min Act: -0.1700
Data Index: 1372477 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5898. Min Act: -0.1700
Data Index: 284621 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5898. Min Act: -0.1700
Data Index: 4264242 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5898. Min Act: -0.1700
Data Index: 2436028 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5273. Min Act: -0.1700
Data Index: 8012085 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5273. Min Act: -0.1700
Data Index: 1421601 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5273. Min Act: -0.1700
Data Index: 8286502 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.4961. Min Act: -0.1700
Data Index: 5566540 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5273. Min Act: -0.1700
Data Index: 7954955 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.4961. Min Act: -0.1700
Data Index: 424856 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.5273. Min Act: -0.1700
Data Index: 315008 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9648. Min Range: -5.9648
Max Act: 5.4961. Min Act: -0.1700
Data Index: 7382523 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19