Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2648. Min Range: -6.2648
Max Act: 6.2648. Min Act: -0.1700
Data Index: 3319010 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2648. Min Range: -6.2648
Max Act: 6.1085. Min Act: -0.1700
Data Index: 2926722 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2648. Min Range: -6.2648
Max Act: 6.0460. Min Act: -0.1700
Data Index: 5634542 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2648. Min Range: -6.2648
Max Act: 6.0460. Min Act: -0.1700
Data Index: 4431552 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2648. Min Range: -6.2648
Max Act: 6.0148. Min Act: -0.1700
Data Index: 8332345 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.9523. Min Act: -0.1700
Data Index: 3441112 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.9523. Min Act: -0.1700
Data Index: 8126515 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.9523. Min Act: -0.1700
Data Index: 8502151 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8898. Min Act: -0.1700
Data Index: 8370632 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8585. Min Act: -0.1700
Data Index: 7880586 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8585. Min Act: -0.1700
Data Index: 1810921 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8273. Min Act: -0.1700
Data Index: 745084 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8273. Min Act: -0.1700
Data Index: 3591922 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8273. Min Act: -0.1700
Data Index: 3827757 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8585. Min Act: -0.1700
Data Index: 3071934 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.7960. Min Act: -0.1700
Data Index: 3612011 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.8273. Min Act: -0.1700
Data Index: 5559084 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.7960. Min Act: -0.1700
Data Index: 4493155 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.7648. Min Act: -0.1700
Data Index: 6589278 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2648. Min Range: -6.2648
Max Act: 5.7648. Min Act: -0.1700
Data Index: 462011 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19