Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.9110. Min Act: -0.1700
Data Index: 2280563 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.8485. Min Act: -0.1700
Data Index: 3967787 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.7860. Min Act: -0.1700
Data Index: 1785614 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.7860. Min Act: -0.1700
Data Index: 2307792 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.6610. Min Act: -0.1700
Data Index: 4453479 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.6610. Min Act: -0.1700
Data Index: 240916 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.5985. Min Act: -0.1700
Data Index: 3269213 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.5360. Min Act: -0.1700
Data Index: 1028214 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.5360. Min Act: -0.1700
Data Index: 1964650 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.5360. Min Act: -0.1700
Data Index: 78168 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.5360. Min Act: -0.1700
Data Index: 4548814 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.5360. Min Act: -0.1700
Data Index: 5085815 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.5360. Min Act: -0.1700
Data Index: 3033454 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.4735. Min Act: -0.1700
Data Index: 7707063 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.4735. Min Act: -0.1700
Data Index: 652313 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.4735. Min Act: -0.1700
Data Index: 7085031 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.4735. Min Act: -0.1700
Data Index: 3641407 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.4735. Min Act: -0.1700
Data Index: 7128877 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.4110. Min Act: -0.1700
Data Index: 59516 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9110. Min Range: -8.9110
Max Act: 8.4110. Min Act: -0.1700
Data Index: 3521988 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19