Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5992. Min Act: -0.1700
Data Index: 4729119 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5680. Min Act: -0.1700
Data Index: 3368641 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5367. Min Act: -0.1700
Data Index: 4210844 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5055. Min Act: -0.1700
Data Index: 313379 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5055. Min Act: -0.1700
Data Index: 8690986 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5055. Min Act: -0.1700
Data Index: 2030774 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5055. Min Act: -0.1700
Data Index: 6171915 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4742. Min Act: -0.1700
Data Index: 7394295 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5055. Min Act: -0.1700
Data Index: 5339186 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 239417 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 4472989 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 7605665 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4117. Min Act: -0.1700
Data Index: 5849021 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 88854 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 2995244 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 3749964 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4430. Min Act: -0.1700
Data Index: 4801413 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4117. Min Act: -0.1700
Data Index: 3539348 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4117. Min Act: -0.1700
Data Index: 2991356 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.4117. Min Act: -0.1700
Data Index: 338703 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19