Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1749 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9304. Min Range: -8.9304
Max Act: 8.9304. Min Act: -0.1700
Data Index: 4948868 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9304. Min Range: -8.9304
Max Act: 8.6804. Min Act: -0.1700
Data Index: 1850256 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9304. Min Range: -8.9304
Max Act: 8.4304. Min Act: -0.1700
Data Index: 7680160 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9304. Min Range: -8.9304
Max Act: 8.1491. Min Act: -0.1700
Data Index: 6967519 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9304. Min Range: -8.9304
Max Act: 8.0866. Min Act: -0.1700
Data Index: 7818654 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9304. Min Range: -8.9304
Max Act: 8.1179. Min Act: -0.1700
Data Index: 4587678 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9304. Min Range: -8.9304
Max Act: 8.0241. Min Act: -0.1700
Data Index: 4093733 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.9929. Min Act: -0.1700
Data Index: 6582682 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.9616. Min Act: -0.1700
Data Index: 8790188 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.9304. Min Act: -0.1700
Data Index: 3275619 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.9616. Min Act: -0.1700
Data Index: 750943 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.9304. Min Act: -0.1700
Data Index: 7073221 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.8991. Min Act: -0.1700
Data Index: 8013060 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.8679. Min Act: -0.1700
Data Index: 692 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.8991. Min Act: -0.1700
Data Index: 2188798 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.8991. Min Act: -0.1700
Data Index: 6919947 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.8679. Min Act: -0.1700
Data Index: 3616480 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.8054. Min Act: -0.1700
Data Index: 340281 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.7741. Min Act: -0.1700
Data Index: 5064846 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9304. Min Range: -8.9304
Max Act: 7.8054. Min Act: -0.1700
Data Index: 806475 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19