Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4924 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.8741. Min Act: -0.1700
Data Index: 8317677 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.7491. Min Act: -0.1700
Data Index: 2307754 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.6866. Min Act: -0.1700
Data Index: 7877116 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.6866. Min Act: -0.1700
Data Index: 5188817 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.6241. Min Act: -0.1700
Data Index: 8651922 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.5616. Min Act: -0.1700
Data Index: 1380351 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.4991. Min Act: -0.1700
Data Index: 1510018 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.5616. Min Act: -0.1700
Data Index: 6043974 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.4366. Min Act: -0.1700
Data Index: 5274463 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.4366. Min Act: -0.1700
Data Index: 1416874 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.2491. Min Act: -0.1700
Data Index: 5218586 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.2491. Min Act: -0.1700
Data Index: 782748 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.2491. Min Act: -0.1700
Data Index: 5265370 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.1866. Min Act: -0.1700
Data Index: 4703280 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.1866. Min Act: -0.1700
Data Index: 706908 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.1866. Min Act: -0.1700
Data Index: 5341708 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.1241. Min Act: -0.1700
Data Index: 202367 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.1866. Min Act: -0.1700
Data Index: 4624016 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.0616. Min Act: -0.1700
Data Index: 8417629 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8741. Min Range: -10.8741
Max Act: 10.1241. Min Act: -0.1700
Data Index: 402251 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19