Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2561 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.4800. Min Act: -0.1700
Data Index: 3429525 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.3238. Min Act: -0.1700
Data Index: 1610338 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.1988. Min Act: -0.1700
Data Index: 2828006 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.1988. Min Act: -0.1700
Data Index: 4556603 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.1988. Min Act: -0.1700
Data Index: 816928 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.1050. Min Act: -0.1700
Data Index: 8410457 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.1363. Min Act: -0.1700
Data Index: 527038 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.0738. Min Act: -0.1700
Data Index: 36530 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.0113. Min Act: -0.1700
Data Index: 2206370 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4800. Min Range: -6.4800
Max Act: 6.0113. Min Act: -0.1700
Data Index: 2187660 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.9800. Min Act: -0.1700
Data Index: 2836277 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.9175. Min Act: -0.1700
Data Index: 3526890 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.9800. Min Act: -0.1700
Data Index: 6869346 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.9488. Min Act: -0.1700
Data Index: 4951929 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.9488. Min Act: -0.1700
Data Index: 7951894 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.9175. Min Act: -0.1700
Data Index: 2168009 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5503104 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5580251 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.8550. Min Act: -0.1700
Data Index: 7816685 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4800. Min Range: -6.4800
Max Act: 5.8550. Min Act: -0.1700
Data Index: 1730222 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19