Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.9938. Min Act: -0.1700
Data Index: 8575166 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.7124. Min Act: -0.1700
Data Index: 8322623 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6811. Min Act: -0.1700
Data Index: 768275 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6655. Min Act: -0.1700
Data Index: 4741481 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6811. Min Act: -0.1700
Data Index: 1885979 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6498. Min Act: -0.1700
Data Index: 5126467 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6498. Min Act: -0.1700
Data Index: 3727889 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6498. Min Act: -0.1700
Data Index: 870766 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6342. Min Act: -0.1700
Data Index: 6375344 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6498. Min Act: -0.1700
Data Index: 4731674 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6342. Min Act: -0.1700
Data Index: 7381366 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6498. Min Act: -0.1700
Data Index: 7484852 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6185. Min Act: -0.1700
Data Index: 2822809 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6185. Min Act: -0.1700
Data Index: 7473603 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6185. Min Act: -0.1700
Data Index: 701444 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6029. Min Act: -0.1700
Data Index: 5098853 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6029. Min Act: -0.1700
Data Index: 1387500 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.5872. Min Act: -0.1700
Data Index: 5308280 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6185. Min Act: -0.1700
Data Index: 3942975 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9938. Min Range: -3.9938
Max Act: 3.6029. Min Act: -0.1700
Data Index: 3084954 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19