Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 567 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.6544. Min Act: -0.1700
Data Index: 1579776 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.5294. Min Act: -0.1700
Data Index: 6201272 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.4669. Min Act: -0.1700
Data Index: 393133 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.4669. Min Act: -0.1700
Data Index: 4182312 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.5294. Min Act: -0.1700
Data Index: 4142780 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.2794. Min Act: -0.1700
Data Index: 3289597 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.2794. Min Act: -0.1700
Data Index: 3323909 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.2169. Min Act: -0.1700
Data Index: 3705979 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.2169. Min Act: -0.1700
Data Index: 1066962 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.1544. Min Act: -0.1700
Data Index: 6262366 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.1544. Min Act: -0.1700
Data Index: 6474412 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.0919. Min Act: -0.1700
Data Index: 6022515 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.0919. Min Act: -0.1700
Data Index: 5205357 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.0919. Min Act: -0.1700
Data Index: 1523563 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.0919. Min Act: -0.1700
Data Index: 6634191 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.0294. Min Act: -0.1700
Data Index: 7913732 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6544. Min Range: -9.6544
Max Act: 8.9669. Min Act: -0.1700
Data Index: 4418206 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6544. Min Range: -9.6544
Max Act: 9.0294. Min Act: -0.1700
Data Index: 6840910 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6544. Min Range: -9.6544
Max Act: 8.9669. Min Act: -0.1700
Data Index: 2078284 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6544. Min Range: -9.6544
Max Act: 8.9669. Min Act: -0.1700
Data Index: 1108628 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19