Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1104 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9797. Min Act: -0.1700
Data Index: 188652 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9481. Min Act: -0.1700
Data Index: 7219723 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9639. Min Act: -0.1700
Data Index: 5260579 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9481. Min Act: -0.1700
Data Index: 4726887 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9322. Min Act: -0.1700
Data Index: 1872344 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9322. Min Act: -0.1700
Data Index: 792687 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9164. Min Act: -0.1700
Data Index: 1712958 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9164. Min Act: -0.1700
Data Index: 8144901 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9164. Min Act: -0.1700
Data Index: 2294079 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9164. Min Act: -0.1700
Data Index: 2524149 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9005. Min Act: -0.1700
Data Index: 4319053 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.8847. Min Act: -0.1700
Data Index: 6795772 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9005. Min Act: -0.1700
Data Index: 6323829 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9005. Min Act: -0.1700
Data Index: 1259489 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.9005. Min Act: -0.1700
Data Index: 4723965 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.8688. Min Act: -0.1700
Data Index: 4261474 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.8688. Min Act: -0.1700
Data Index: 3480002 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.8529. Min Act: -0.1700
Data Index: 2408924 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.8688. Min Act: -0.1700
Data Index: 7222053 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9797. Min Range: -2.9797
Max Act: 2.8529. Min Act: -0.1700
Data Index: 6984890 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19