Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5447 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.6993. Min Act: -0.1700
Data Index: 1807828 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.5431. Min Act: -0.1700
Data Index: 8089574 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.4806. Min Act: -0.1700
Data Index: 8757409 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.3243. Min Act: -0.1700
Data Index: 359238 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.3243. Min Act: -0.1700
Data Index: 4216055 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.3243. Min Act: -0.1700
Data Index: 5812186 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.2618. Min Act: -0.1700
Data Index: 6056780 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.3243. Min Act: -0.1700
Data Index: 1292613 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.2931. Min Act: -0.1700
Data Index: 1540686 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.2618. Min Act: -0.1700
Data Index: 4813003 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.2618. Min Act: -0.1700
Data Index: 5660360 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.2306. Min Act: -0.1700
Data Index: 6928463 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1993. Min Act: -0.1700
Data Index: 3449303 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1681. Min Act: -0.1700
Data Index: 7215396 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1681. Min Act: -0.1700
Data Index: 7866391 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1681. Min Act: -0.1700
Data Index: 1911770 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1681. Min Act: -0.1700
Data Index: 2101697 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1056. Min Act: -0.1700
Data Index: 908780 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1368. Min Act: -0.1700
Data Index: 4786474 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6993. Min Range: -5.6993
Max Act: 5.1056. Min Act: -0.1700
Data Index: 5775116 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19