Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 507 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.5058. Min Act: -0.1700
Data Index: 5597640 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.3495. Min Act: -0.1700
Data Index: 5110870 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.3183. Min Act: -0.1700
Data Index: 3776676 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.2245. Min Act: -0.1700
Data Index: 2122202 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.2245. Min Act: -0.1700
Data Index: 1828764 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.1933. Min Act: -0.1700
Data Index: 2745006 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.1620. Min Act: -0.1700
Data Index: 582211 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.1620. Min Act: -0.1700
Data Index: 4146273 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.1620. Min Act: -0.1700
Data Index: 6710611 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0995. Min Act: -0.1700
Data Index: 8608858 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0995. Min Act: -0.1700
Data Index: 6292818 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0995. Min Act: -0.1700
Data Index: 2087740 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0683. Min Act: -0.1700
Data Index: 6843818 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0370. Min Act: -0.1700
Data Index: 2590253 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0370. Min Act: -0.1700
Data Index: 1931612 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0058. Min Act: -0.1700
Data Index: 8082177 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0058. Min Act: -0.1700
Data Index: 2564374 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0370. Min Act: -0.1700
Data Index: 8620792 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5058. Min Range: -6.5058
Max Act: 6.0370. Min Act: -0.1700
Data Index: 4703745 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5058. Min Range: -6.5058
Max Act: 5.9745. Min Act: -0.1700
Data Index: 2265477 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19