Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.7798. Min Act: -0.1700
Data Index: 3323668 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.3736. Min Act: -0.1700
Data Index: 411590 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.3736. Min Act: -0.1700
Data Index: 1606144 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.3423. Min Act: -0.1700
Data Index: 7386477 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.3111. Min Act: -0.1700
Data Index: 1337633 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.2798. Min Act: -0.1700
Data Index: 8557482 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.2486. Min Act: -0.1700
Data Index: 3964592 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.2486. Min Act: -0.1700
Data Index: 1403601 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.2173. Min Act: -0.1700
Data Index: 1066755 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.1861. Min Act: -0.1700
Data Index: 4592421 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.1861. Min Act: -0.1700
Data Index: 1247119 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.1548. Min Act: -0.1700
Data Index: 3846520 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.1236. Min Act: -0.1700
Data Index: 405074 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.1236. Min Act: -0.1700
Data Index: 5528623 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.0610. Min Act: -0.1700
Data Index: 7587108 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.0923. Min Act: -0.1700
Data Index: 886822 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.0923. Min Act: -0.1700
Data Index: 5073661 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.1236. Min Act: -0.1700
Data Index: 8258938 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.0610. Min Act: -0.1700
Data Index: 4371858 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7798. Min Range: -4.7798
Max Act: 4.0610. Min Act: -0.1700
Data Index: 8576913 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19