Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1085 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6728. Min Range: -4.6728
Max Act: 4.6728. Min Act: -0.1700
Data Index: 4370850 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6728. Min Range: -4.6728
Max Act: 4.5791. Min Act: -0.1700
Data Index: 4278052 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6728. Min Range: -4.6728
Max Act: 4.0790. Min Act: -0.1700
Data Index: 5045003 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6728. Min Range: -4.6728
Max Act: 4.0790. Min Act: -0.1700
Data Index: 413107 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6728. Min Range: -4.6728
Max Act: 4.0790. Min Act: -0.1700
Data Index: 5044999 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.9852. Min Act: -0.1700
Data Index: 5381774 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.9852. Min Act: -0.1700
Data Index: 7656964 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.9227. Min Act: -0.1700
Data Index: 2424993 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.9540. Min Act: -0.1700
Data Index: 5649643 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.9227. Min Act: -0.1700
Data Index: 522129 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.9227. Min Act: -0.1700
Data Index: 413109 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.9227. Min Act: -0.1700
Data Index: 8226826 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8914. Min Act: -0.1700
Data Index: 2024990 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8914. Min Act: -0.1700
Data Index: 808928 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8602. Min Act: -0.1700
Data Index: 2024991 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8602. Min Act: -0.1700
Data Index: 7817597 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8602. Min Act: -0.1700
Data Index: 6291950 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8914. Min Act: -0.1700
Data Index: 2847795 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8602. Min Act: -0.1700
Data Index: 8330428 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6728. Min Range: -4.6728
Max Act: 3.8602. Min Act: -0.1700
Data Index: 5920967 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19