Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0308. Min Range: -8.0308
Max Act: 8.0308. Min Act: -0.1700
Data Index: 5431565 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.9683. Min Act: -0.1700
Data Index: 762230 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.9371. Min Act: -0.1700
Data Index: 1869730 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.7183. Min Act: -0.1700
Data Index: 5136709 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.7183. Min Act: -0.1700
Data Index: 164098 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.6871. Min Act: -0.1700
Data Index: 8050440 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.6558. Min Act: -0.1700
Data Index: 4998624 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.6558. Min Act: -0.1700
Data Index: 1270532 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.6246. Min Act: -0.1700
Data Index: 6770772 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5621. Min Act: -0.1700
Data Index: 1579997 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5308. Min Act: -0.1700
Data Index: 5078550 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5308. Min Act: -0.1700
Data Index: 8614640 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4996. Min Act: -0.1700
Data Index: 8110206 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4371. Min Act: -0.1700
Data Index: 5292419 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4371. Min Act: -0.1700
Data Index: 3041206 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.3746. Min Act: -0.1700
Data Index: 6882041 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.3433. Min Act: -0.1700
Data Index: 1452530 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.3433. Min Act: -0.1700
Data Index: 2238327 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.3433. Min Act: -0.1700
Data Index: 1257351 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.3433. Min Act: -0.1700
Data Index: 3666535 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19