Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3634 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 7893037 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 4785614 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.1386. Min Act: -0.1700
Data Index: 7651906 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.1386. Min Act: -0.1700
Data Index: 3776044 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.1074. Min Act: -0.1700
Data Index: 7025745 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.1386. Min Act: -0.1700
Data Index: 3181464 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.0761. Min Act: -0.1700
Data Index: 8746327 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.0761. Min Act: -0.1700
Data Index: 3520662 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.0449. Min Act: -0.1700
Data Index: 3744543 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.0449. Min Act: -0.1700
Data Index: 4290390 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.0136. Min Act: -0.1700
Data Index: 2163190 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.9824. Min Act: -0.1700
Data Index: 4935620 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.9824. Min Act: -0.1700
Data Index: 487167 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.9199. Min Act: -0.1700
Data Index: 7522785 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.8886. Min Act: -0.1700
Data Index: 6258854 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.9199. Min Act: -0.1700
Data Index: 582770 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.8886. Min Act: -0.1700
Data Index: 8145606 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.8886. Min Act: -0.1700
Data Index: 6573168 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.9199. Min Act: -0.1700
Data Index: 542642 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.8886. Min Act: -0.1700
Data Index: 3082829 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19