Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.6767. Min Act: -0.1700
Data Index: 1644908 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.4892. Min Act: -0.1700
Data Index: 6976528 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.4892. Min Act: -0.1700
Data Index: 1563851 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.4267. Min Act: -0.1700
Data Index: 1616588 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.4267. Min Act: -0.1700
Data Index: 8498542 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.3017. Min Act: -0.1700
Data Index: 6445683 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.2392. Min Act: -0.1700
Data Index: 1616591 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.2392. Min Act: -0.1700
Data Index: 4578407 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.1767. Min Act: -0.1700
Data Index: 3158952 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.1767. Min Act: -0.1700
Data Index: 1778152 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.1142. Min Act: -0.1700
Data Index: 5162321 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.1142. Min Act: -0.1700
Data Index: 38570 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.1142. Min Act: -0.1700
Data Index: 7899415 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.1142. Min Act: -0.1700
Data Index: 5788271 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.1142. Min Act: -0.1700
Data Index: 1563853 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.0517. Min Act: -0.1700
Data Index: 3599295 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6767. Min Range: -8.6767
Max Act: 8.0517. Min Act: -0.1700
Data Index: 8498541 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6767. Min Range: -8.6767
Max Act: 7.9892. Min Act: -0.1700
Data Index: 1778169 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6767. Min Range: -8.6767
Max Act: 7.9892. Min Act: -0.1700
Data Index: 4937039 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6767. Min Range: -8.6767
Max Act: 7.9892. Min Act: -0.1700
Data Index: 4649188 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19