Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.3185. Min Act: -0.1700
Data Index: 5657425 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.2873. Min Act: -0.1700
Data Index: 4126869 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.1623. Min Act: -0.1700
Data Index: 8045605 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.0998. Min Act: -0.1700
Data Index: 8769276 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.0998. Min Act: -0.1700
Data Index: 7018141 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.0685. Min Act: -0.1700
Data Index: 528872 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.0373. Min Act: -0.1700
Data Index: 1876792 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.9748. Min Act: -0.1700
Data Index: 2406024 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3185. Min Range: -6.3185
Max Act: 6.0060. Min Act: -0.1700
Data Index: 4045152 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.9123. Min Act: -0.1700
Data Index: 4413176 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.9435. Min Act: -0.1700
Data Index: 4893433 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.9123. Min Act: -0.1700
Data Index: 5788592 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.9123. Min Act: -0.1700
Data Index: 6038203 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.8810. Min Act: -0.1700
Data Index: 7609989 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.8810. Min Act: -0.1700
Data Index: 1791592 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.9123. Min Act: -0.1700
Data Index: 2497723 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.8810. Min Act: -0.1700
Data Index: 7723294 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.8810. Min Act: -0.1700
Data Index: 743780 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.8498. Min Act: -0.1700
Data Index: 7949936 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3185. Min Range: -6.3185
Max Act: 5.8498. Min Act: -0.1700
Data Index: 4239589 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19