Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.4767. Min Act: -0.1700
Data Index: 2796524 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.3205. Min Act: -0.1700
Data Index: 4614079 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.2580. Min Act: -0.1700
Data Index: 6081661 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.2580. Min Act: -0.1700
Data Index: 1418452 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.2580. Min Act: -0.1700
Data Index: 5494622 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.2267. Min Act: -0.1700
Data Index: 6800460 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1955. Min Act: -0.1700
Data Index: 7223096 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1955. Min Act: -0.1700
Data Index: 3838438 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1955. Min Act: -0.1700
Data Index: 3391788 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1330. Min Act: -0.1700
Data Index: 1887822 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1642. Min Act: -0.1700
Data Index: 8278703 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1330. Min Act: -0.1700
Data Index: 1419905 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1017. Min Act: -0.1700
Data Index: 8167359 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1330. Min Act: -0.1700
Data Index: 8012788 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1330. Min Act: -0.1700
Data Index: 7313223 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1017. Min Act: -0.1700
Data Index: 4167307 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.1330. Min Act: -0.1700
Data Index: 711267 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.0705. Min Act: -0.1700
Data Index: 5756903 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.0705. Min Act: -0.1700
Data Index: 7690470 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4767. Min Range: -5.4767
Max Act: 5.0705. Min Act: -0.1700
Data Index: 3344532 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19