Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0998. Min Range: -8.0998
Max Act: 8.0998. Min Act: -0.1700
Data Index: 7926886 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0998. Min Range: -8.0998
Max Act: 8.0373. Min Act: -0.1700
Data Index: 1860413 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.9123. Min Act: -0.1700
Data Index: 6989241 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.8498. Min Act: -0.1700
Data Index: 7282796 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.8498. Min Act: -0.1700
Data Index: 4249675 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.8498. Min Act: -0.1700
Data Index: 1211410 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.7248. Min Act: -0.1700
Data Index: 4754253 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.7248. Min Act: -0.1700
Data Index: 2525924 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.7248. Min Act: -0.1700
Data Index: 7413114 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.7248. Min Act: -0.1700
Data Index: 3693807 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.7248. Min Act: -0.1700
Data Index: 784491 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.7248. Min Act: -0.1700
Data Index: 12607 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.7248. Min Act: -0.1700
Data Index: 2063642 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.6623. Min Act: -0.1700
Data Index: 5692399 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.6623. Min Act: -0.1700
Data Index: 5655922 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.6623. Min Act: -0.1700
Data Index: 48995 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.5998. Min Act: -0.1700
Data Index: 8465592 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.5998. Min Act: -0.1700
Data Index: 5964644 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.5998. Min Act: -0.1700
Data Index: 5792980 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0998. Min Range: -8.0998
Max Act: 7.5998. Min Act: -0.1700
Data Index: 1465247 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19