Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0601. Min Range: -6.0601
Max Act: 6.0601. Min Act: -0.1700
Data Index: 4333183 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.9663. Min Act: -0.1700
Data Index: 162722 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.9038. Min Act: -0.1700
Data Index: 8435154 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8726. Min Act: -0.1700
Data Index: 1890759 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8101. Min Act: -0.1700
Data Index: 3177892 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8101. Min Act: -0.1700
Data Index: 8537222 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.8101. Min Act: -0.1700
Data Index: 2494946 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7476. Min Act: -0.1700
Data Index: 6750927 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7476. Min Act: -0.1700
Data Index: 2951187 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7476. Min Act: -0.1700
Data Index: 7440283 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.7476. Min Act: -0.1700
Data Index: 7636858 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.6851. Min Act: -0.1700
Data Index: 4243048 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.6851. Min Act: -0.1700
Data Index: 6483335 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.6851. Min Act: -0.1700
Data Index: 5853755 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.6538. Min Act: -0.1700
Data Index: 2371403 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.6226. Min Act: -0.1700
Data Index: 4408127 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.6226. Min Act: -0.1700
Data Index: 825697 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.6226. Min Act: -0.1700
Data Index: 5854695 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.5913. Min Act: -0.1700
Data Index: 1201420 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0601. Min Range: -6.0601
Max Act: 5.5913. Min Act: -0.1700
Data Index: 8277297 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19