Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 2970916 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 596606 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0041. Min Act: -0.1700
Data Index: 5570576 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 7195938 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 593148 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 5799609 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9416. Min Act: -0.1700
Data Index: 5822387 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 3461390 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 7600890 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 7806632 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 6503697 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 6737237 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8791. Min Act: -0.1700
Data Index: 7376180 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8791. Min Act: -0.1700
Data Index: 3333896 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 4928815 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 5647805 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8166. Min Act: -0.1700
Data Index: 8102693 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8166. Min Act: -0.1700
Data Index: 3328857 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 3672044 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8166. Min Act: -0.1700
Data Index: 8214699 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19