Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5230 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2813. Min Range: -7.2813
Max Act: 7.2813. Min Act: -0.1700
Data Index: 6111176 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2813. Min Range: -7.2813
Max Act: 7.2188. Min Act: -0.1700
Data Index: 3171126 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2813. Min Range: -7.2813
Max Act: 7.0625. Min Act: -0.1700
Data Index: 764192 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2813. Min Range: -7.2813
Max Act: 7.0000. Min Act: -0.1700
Data Index: 3793061 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9375. Min Act: -0.1700
Data Index: 5021661 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9063. Min Act: -0.1700
Data Index: 675377 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9063. Min Act: -0.1700
Data Index: 5072281 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9063. Min Act: -0.1700
Data Index: 1588153 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9063. Min Act: -0.1700
Data Index: 8491016 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9063. Min Act: -0.1700
Data Index: 3917508 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9063. Min Act: -0.1700
Data Index: 6513625 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.9063. Min Act: -0.1700
Data Index: 7806412 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8750. Min Act: -0.1700
Data Index: 8320651 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8750. Min Act: -0.1700
Data Index: 1420597 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8750. Min Act: -0.1700
Data Index: 7246547 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8438. Min Act: -0.1700
Data Index: 861203 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8125. Min Act: -0.1700
Data Index: 5688392 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8125. Min Act: -0.1700
Data Index: 3706458 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8125. Min Act: -0.1700
Data Index: 8357170 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2813. Min Range: -7.2813
Max Act: 6.8125. Min Act: -0.1700
Data Index: 6979548 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19