Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4548 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.3936. Min Act: -0.1700
Data Index: 248984 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.2686. Min Act: -0.1700
Data Index: 408505 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.2061. Min Act: -0.1700
Data Index: 8071637 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.1124. Min Act: -0.1700
Data Index: 1153987 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.0811. Min Act: -0.1700
Data Index: 6721396 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.0499. Min Act: -0.1700
Data Index: 4841619 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.0186. Min Act: -0.1700
Data Index: 1119684 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9874. Min Act: -0.1700
Data Index: 770760 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9874. Min Act: -0.1700
Data Index: 4136568 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9561. Min Act: -0.1700
Data Index: 5171513 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9561. Min Act: -0.1700
Data Index: 3055809 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9561. Min Act: -0.1700
Data Index: 198318 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9249. Min Act: -0.1700
Data Index: 7364363 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9561. Min Act: -0.1700
Data Index: 3586480 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9249. Min Act: -0.1700
Data Index: 1561776 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.8936. Min Act: -0.1700
Data Index: 899664 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.8936. Min Act: -0.1700
Data Index: 1333908 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.8936. Min Act: -0.1700
Data Index: 5225773 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.8624. Min Act: -0.1700
Data Index: 4618554 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.8624. Min Act: -0.1700
Data Index: 3211974 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19