Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.9065. Min Act: -0.1700
Data Index: 5891686 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.7502. Min Act: -0.1700
Data Index: 5850576 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.6565. Min Act: -0.1700
Data Index: 2785540 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.6877. Min Act: -0.1700
Data Index: 7750457 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.6565. Min Act: -0.1700
Data Index: 3904995 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.6565. Min Act: -0.1700
Data Index: 6500232 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5940. Min Act: -0.1700
Data Index: 5512286 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5940. Min Act: -0.1700
Data Index: 5474323 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.6252. Min Act: -0.1700
Data Index: 5771838 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5627. Min Act: -0.1700
Data Index: 6911806 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5627. Min Act: -0.1700
Data Index: 4763418 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5315. Min Act: -0.1700
Data Index: 7769990 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5315. Min Act: -0.1700
Data Index: 7911537 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5315. Min Act: -0.1700
Data Index: 8365212 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5315. Min Act: -0.1700
Data Index: 7380847 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.4690. Min Act: -0.1700
Data Index: 210861 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5002. Min Act: -0.1700
Data Index: 1065988 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.5315. Min Act: -0.1700
Data Index: 756788 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.4690. Min Act: -0.1700
Data Index: 3677389 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9065. Min Range: -4.9065
Max Act: 4.4690. Min Act: -0.1700
Data Index: 6480058 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19