Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5269. Min Range: -7.5269
Max Act: 7.5269. Min Act: -0.1700
Data Index: 6368513 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5269. Min Range: -7.5269
Max Act: 7.4332. Min Act: -0.1700
Data Index: 1095235 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5269. Min Range: -7.5269
Max Act: 7.0269. Min Act: -0.1700
Data Index: 7327642 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9957. Min Act: -0.1700
Data Index: 4427660 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9957. Min Act: -0.1700
Data Index: 903082 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9644. Min Act: -0.1700
Data Index: 4509509 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9019. Min Act: -0.1700
Data Index: 1412696 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9332. Min Act: -0.1700
Data Index: 314897 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9644. Min Act: -0.1700
Data Index: 704236 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9332. Min Act: -0.1700
Data Index: 7757575 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.8707. Min Act: -0.1700
Data Index: 916681 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.8707. Min Act: -0.1700
Data Index: 6745393 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9019. Min Act: -0.1700
Data Index: 179481 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.9019. Min Act: -0.1700
Data Index: 1851350 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.8394. Min Act: -0.1700
Data Index: 7137577 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7667185 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.8394. Min Act: -0.1700
Data Index: 1139344 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.8394. Min Act: -0.1700
Data Index: 2286753 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7746520 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5269. Min Range: -7.5269
Max Act: 6.7769. Min Act: -0.1700
Data Index: 3910381 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19