Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.6625. Min Act: -0.1700
Data Index: 1321500 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.5687. Min Act: -0.1700
Data Index: 6279519 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4750. Min Act: -0.1700
Data Index: 5039349 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.3812. Min Act: -0.1700
Data Index: 3040786 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.3812. Min Act: -0.1700
Data Index: 8239674 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.3187. Min Act: -0.1700
Data Index: 7938397 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.2562. Min Act: -0.1700
Data Index: 7028210 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.2562. Min Act: -0.1700
Data Index: 8277139 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.2249. Min Act: -0.1700
Data Index: 5604174 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.2249. Min Act: -0.1700
Data Index: 554603 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.2249. Min Act: -0.1700
Data Index: 6980074 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.2249. Min Act: -0.1700
Data Index: 5014503 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.1937. Min Act: -0.1700
Data Index: 6248860 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.1624. Min Act: -0.1700
Data Index: 1242386 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.1624. Min Act: -0.1700
Data Index: 2666067 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.1312. Min Act: -0.1700
Data Index: 1245376 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.1312. Min Act: -0.1700
Data Index: 5512973 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.1312. Min Act: -0.1700
Data Index: 123288 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.1312. Min Act: -0.1700
Data Index: 4698428 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.0999. Min Act: -0.1700
Data Index: 2909046 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19