Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6776. Min Act: -0.1700
Data Index: 8810216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6602. Min Act: -0.1275
Data Index: 7496770 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6602. Min Act: -0.1700
Data Index: 234625 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6428. Min Act: -0.1700
Data Index: 6562047 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6254. Min Act: -0.1700
Data Index: 5598758 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6254. Min Act: -0.1700
Data Index: 4993134 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6079. Min Act: -0.1700
Data Index: 8647418 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6428. Min Act: -0.1700
Data Index: 6314192 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6079. Min Act: -0.1700
Data Index: 2516532 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6079. Min Act: -0.1700
Data Index: 4314171 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.6079. Min Act: -0.1700
Data Index: 3854750 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5905. Min Act: -0.1700
Data Index: 7407526 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5905. Min Act: -0.1700
Data Index: 2439238 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5905. Min Act: -0.1700
Data Index: 2124562 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5905. Min Act: -0.1700
Data Index: 1769288 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5905. Min Act: -0.1700
Data Index: 8080874 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5730. Min Act: -0.1700
Data Index: 6011715 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5730. Min Act: -0.1700
Data Index: 2339332 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5730. Min Act: -0.1700
Data Index: 6514096 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6776. Min Range: -1.6776
Max Act: 1.5730. Min Act: -0.1700
Data Index: 1129566 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19