Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4081. Min Range: -6.4081
Max Act: 6.4081. Min Act: -0.1700
Data Index: 6450591 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4081. Min Range: -6.4081
Max Act: 6.2518. Min Act: -0.1700
Data Index: 4087655 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4081. Min Range: -6.4081
Max Act: 6.1581. Min Act: -0.1700
Data Index: 7531395 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4081. Min Range: -6.4081
Max Act: 6.1893. Min Act: -0.1700
Data Index: 2395455 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4081. Min Range: -6.4081
Max Act: 6.0331. Min Act: -0.1700
Data Index: 468483 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4081. Min Range: -6.4081
Max Act: 6.0018. Min Act: -0.1700
Data Index: 6666385 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4081. Min Range: -6.4081
Max Act: 6.0018. Min Act: -0.1700
Data Index: 2998450 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.9706. Min Act: -0.1700
Data Index: 5316376 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.9393. Min Act: -0.1700
Data Index: 5922866 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.9393. Min Act: -0.1700
Data Index: 4591850 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8768. Min Act: -0.1700
Data Index: 6102716 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.9081. Min Act: -0.1700
Data Index: 6785638 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.9081. Min Act: -0.1700
Data Index: 8499253 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8456. Min Act: -0.1700
Data Index: 869387 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8768. Min Act: -0.1700
Data Index: 1464739 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8456. Min Act: -0.1700
Data Index: 8761269 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8456. Min Act: -0.1700
Data Index: 3278728 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8456. Min Act: -0.1700
Data Index: 1129178 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8143. Min Act: -0.1700
Data Index: 4807382 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4081. Min Range: -6.4081
Max Act: 5.8456. Min Act: -0.1700
Data Index: 5034036 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19