Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.8115. Min Act: -0.1700
Data Index: 7172509 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.7490. Min Act: -0.1700
Data Index: 2436863 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.6865. Min Act: -0.1700
Data Index: 4223713 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.7177. Min Act: -0.1700
Data Index: 3436048 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.6552. Min Act: -0.1700
Data Index: 4572520 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.6240. Min Act: -0.1700
Data Index: 5120602 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.6240. Min Act: -0.1700
Data Index: 4696073 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.5927. Min Act: -0.1700
Data Index: 8071393 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.5927. Min Act: -0.1700
Data Index: 8164341 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.5615. Min Act: -0.1700
Data Index: 3546387 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4990. Min Act: -0.1700
Data Index: 243688 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4990. Min Act: -0.1700
Data Index: 2171001 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4677. Min Act: -0.1700
Data Index: 57938 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4677. Min Act: -0.1700
Data Index: 4315544 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4365. Min Act: -0.1700
Data Index: 6825413 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4052. Min Act: -0.1700
Data Index: 4570177 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4052. Min Act: -0.1700
Data Index: 6265832 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4052. Min Act: -0.1700
Data Index: 6950480 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.4052. Min Act: -0.1700
Data Index: 4347885 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8115. Min Range: -6.8115
Max Act: 6.3427. Min Act: -0.1700
Data Index: 1634800 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19