Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2223 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2155. Min Range: -6.2155
Max Act: 6.2155. Min Act: -0.1700
Data Index: 5908805 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2155. Min Range: -6.2155
Max Act: 6.0280. Min Act: -0.1700
Data Index: 7271860 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.8717. Min Act: -0.1700
Data Index: 6033489 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.7780. Min Act: -0.1700
Data Index: 4839204 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.8092. Min Act: -0.1700
Data Index: 674520 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.7780. Min Act: -0.1700
Data Index: 8347698 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.7467. Min Act: -0.1700
Data Index: 604857 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.7467. Min Act: -0.1700
Data Index: 1676670 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.7155. Min Act: -0.1700
Data Index: 6398956 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.6530. Min Act: -0.1700
Data Index: 7276662 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.6217. Min Act: -0.1700
Data Index: 7636400 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.6530. Min Act: -0.1700
Data Index: 7777660 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.6530. Min Act: -0.1700
Data Index: 1312165 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.5905. Min Act: -0.1700
Data Index: 3923604 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.6217. Min Act: -0.1700
Data Index: 5148538 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.5905. Min Act: -0.1700
Data Index: 8743234 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.5905. Min Act: -0.1700
Data Index: 1815973 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.5280. Min Act: -0.1700
Data Index: 1774574 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.5592. Min Act: -0.1700
Data Index: 7861195 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2155. Min Range: -6.2155
Max Act: 5.5592. Min Act: -0.1700
Data Index: 710062 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19