Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 559 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.6404. Min Act: -0.1700
Data Index: 2361763 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.5779. Min Act: -0.1700
Data Index: 870488 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.5466. Min Act: -0.1700
Data Index: 1426907 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.5466. Min Act: -0.1700
Data Index: 6904231 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.5779. Min Act: -0.1700
Data Index: 1141176 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 3900352 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.5154. Min Act: -0.1700
Data Index: 5513830 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4841. Min Act: -0.1700
Data Index: 3940691 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4841. Min Act: -0.1700
Data Index: 1366418 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4841. Min Act: -0.1700
Data Index: 3529727 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4529. Min Act: -0.1700
Data Index: 2929786 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4529. Min Act: -0.1700
Data Index: 6831793 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4529. Min Act: -0.1700
Data Index: 5592987 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4216. Min Act: -0.1700
Data Index: 3517719 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4216. Min Act: -0.1700
Data Index: 3975631 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4216. Min Act: -0.1700
Data Index: 2340377 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4216. Min Act: -0.1700
Data Index: 1310145 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4216. Min Act: -0.1700
Data Index: 739319 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.3904. Min Act: -0.1700
Data Index: 4229516 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6404. Min Range: -4.6404
Max Act: 4.4216. Min Act: -0.1700
Data Index: 6033465 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19