Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.6081. Min Act: -0.1700
Data Index: 618358 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.3894. Min Act: -0.1700
Data Index: 4812719 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.3269. Min Act: -0.1700
Data Index: 4969930 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.2956. Min Act: -0.1700
Data Index: 1523473 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.2019. Min Act: -0.1700
Data Index: 353154 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.1706. Min Act: -0.1700
Data Index: 6470104 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.1394. Min Act: -0.1700
Data Index: 5060664 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.0144. Min Act: -0.1700
Data Index: 2604725 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6081. Min Range: -7.6081
Max Act: 7.0144. Min Act: -0.1700
Data Index: 8128357 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9519. Min Act: -0.1700
Data Index: 5278456 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9831. Min Act: -0.1700
Data Index: 2072713 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9831. Min Act: -0.1700
Data Index: 3095049 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9519. Min Act: -0.1700
Data Index: 4625876 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9519. Min Act: -0.1700
Data Index: 8317905 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9831. Min Act: -0.1700
Data Index: 5278448 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9519. Min Act: -0.1700
Data Index: 1811767 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.9206. Min Act: -0.1700
Data Index: 8325314 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.8894. Min Act: -0.1700
Data Index: 2580185 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.8894. Min Act: -0.1700
Data Index: 4392259 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6081. Min Range: -7.6081
Max Act: 6.8581. Min Act: -0.1700
Data Index: 5055125 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19