Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1200 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0058. Min Range: -8.0058
Max Act: 8.0058. Min Act: -0.1700
Data Index: 7336846 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.8183. Min Act: -0.1700
Data Index: 2740728 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5995. Min Act: -0.1700
Data Index: 885619 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5370. Min Act: -0.1700
Data Index: 7532475 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5683. Min Act: -0.1700
Data Index: 956460 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.5995. Min Act: -0.1700
Data Index: 2928243 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.4745. Min Act: -0.1700
Data Index: 8583629 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3495. Min Act: -0.1700
Data Index: 5141053 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.3495. Min Act: -0.1700
Data Index: 6637803 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.2870. Min Act: -0.1700
Data Index: 6941047 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.1933. Min Act: -0.1700
Data Index: 3972666 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.1933. Min Act: -0.1700
Data Index: 4876640 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.0995. Min Act: -0.1700
Data Index: 1779010 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.0683. Min Act: -0.1700
Data Index: 312476 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.0370. Min Act: -0.1700
Data Index: 4800258 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0058. Min Range: -8.0058
Max Act: 7.0058. Min Act: -0.1700
Data Index: 5261008 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0058. Min Range: -8.0058
Max Act: 6.9745. Min Act: -0.1700
Data Index: 7975474 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0058. Min Range: -8.0058
Max Act: 6.9433. Min Act: -0.1700
Data Index: 5372218 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0058. Min Range: -8.0058
Max Act: 6.9433. Min Act: -0.1700
Data Index: 4527835 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0058. Min Range: -8.0058
Max Act: 6.9120. Min Act: -0.1700
Data Index: 454266 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19