Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2721. Min Range: -9.2721
Max Act: 9.2721. Min Act: -0.1700
Data Index: 3375426 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2721. Min Range: -9.2721
Max Act: 8.8346. Min Act: -0.1700
Data Index: 6145114 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2721. Min Range: -9.2721
Max Act: 8.2721. Min Act: -0.1700
Data Index: 6131510 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2721. Min Range: -9.2721
Max Act: 8.2096. Min Act: -0.1700
Data Index: 4230522 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2721. Min Range: -9.2721
Max Act: 8.1159. Min Act: -0.1700
Data Index: 2162245 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2721. Min Range: -9.2721
Max Act: 8.0534. Min Act: -0.1700
Data Index: 3985463 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2721. Min Range: -9.2721
Max Act: 8.0534. Min Act: -0.1700
Data Index: 8448414 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.9909. Min Act: -0.1700
Data Index: 7519515 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.9596. Min Act: -0.1700
Data Index: 6620466 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.9284. Min Act: -0.1700
Data Index: 7779116 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.9284. Min Act: -0.1700
Data Index: 1639837 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.8971. Min Act: -0.1700
Data Index: 1022038 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 5292500 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 7977687 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 398155 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.8034. Min Act: -0.1700
Data Index: 3618200 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.8034. Min Act: -0.1700
Data Index: 946689 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.8034. Min Act: -0.1700
Data Index: 4189207 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 519322 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2721. Min Range: -9.2721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 5649051 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19