Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.6081. Min Act: -0.1700
Data Index: 438182 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.5769. Min Act: -0.1700
Data Index: 5506439 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.3894. Min Act: -0.1700
Data Index: 588023 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.3894. Min Act: -0.1700
Data Index: 2918028 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.3894. Min Act: -0.1700
Data Index: 8020496 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.3894. Min Act: -0.1700
Data Index: 851715 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.3581. Min Act: -0.1700
Data Index: 2245974 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.3269. Min Act: -0.1700
Data Index: 6762773 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.2644. Min Act: -0.1700
Data Index: 4913385 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.2956. Min Act: -0.1700
Data Index: 4834040 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.2956. Min Act: -0.1700
Data Index: 6708289 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.2331. Min Act: -0.1700
Data Index: 2926983 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.2019. Min Act: -0.1700
Data Index: 3606746 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.1706. Min Act: -0.1700
Data Index: 368441 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.1706. Min Act: -0.1700
Data Index: 7441609 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.1394. Min Act: -0.1700
Data Index: 4816452 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.1394. Min Act: -0.1700
Data Index: 8101508 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.1081. Min Act: -0.1700
Data Index: 2508112 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.0769. Min Act: -0.1700
Data Index: 151318 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6081. Min Range: -6.6081
Max Act: 6.1081. Min Act: -0.1700
Data Index: 4059926 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19