Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4779 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1350. Min Range: -9.1350
Max Act: 9.1350. Min Act: -0.1700
Data Index: 3893906 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.8850. Min Act: -0.1700
Data Index: 4391745 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.7600. Min Act: -0.1700
Data Index: 8507677 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.6350. Min Act: -0.1700
Data Index: 5132909 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.6350. Min Act: -0.1700
Data Index: 523043 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.5725. Min Act: -0.1700
Data Index: 5399183 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.5725. Min Act: -0.1700
Data Index: 211846 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.5100. Min Act: -0.1700
Data Index: 6239785 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.5100. Min Act: -0.1700
Data Index: 4012442 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 7585396 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 6335773 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 1790569 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 7950619 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 7439666 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 5502235 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 6778771 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.4475. Min Act: -0.1700
Data Index: 6536667 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.3850. Min Act: -0.1700
Data Index: 7833354 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.3850. Min Act: -0.1700
Data Index: 4234467 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1350. Min Range: -9.1350
Max Act: 8.3850. Min Act: -0.1700
Data Index: 4853640 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19