Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1138 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.8096. Min Act: -0.1700
Data Index: 5135363 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.7784. Min Act: -0.1700
Data Index: 2353979 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.5284. Min Act: -0.1700
Data Index: 7089377 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.4034. Min Act: -0.1700
Data Index: 852271 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.3096. Min Act: -0.1700
Data Index: 725270 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.3096. Min Act: -0.1700
Data Index: 7248725 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.2471. Min Act: -0.1700
Data Index: 3255907 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.2471. Min Act: -0.1700
Data Index: 5590821 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.2471. Min Act: -0.1700
Data Index: 5637550 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.2471. Min Act: -0.1700
Data Index: 7711628 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.1534. Min Act: -0.1700
Data Index: 6648370 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.1534. Min Act: -0.1700
Data Index: 452029 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.1221. Min Act: -0.1700
Data Index: 5624539 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.0909. Min Act: -0.1700
Data Index: 4813284 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.1221. Min Act: -0.1700
Data Index: 1746660 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.0909. Min Act: -0.1700
Data Index: 5323659 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.0596. Min Act: -0.1700
Data Index: 6050395 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.0596. Min Act: -0.1700
Data Index: 1468429 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.0284. Min Act: -0.1700
Data Index: 6906590 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8096. Min Range: -7.8096
Max Act: 7.0284. Min Act: -0.1700
Data Index: 2847103 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19