Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.9648. Min Act: -0.1700
Data Index: 3468224 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.9648. Min Act: -0.1700
Data Index: 2898087 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.9648. Min Act: -0.1700
Data Index: 6838526 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.8398. Min Act: -0.1700
Data Index: 666760 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.8398. Min Act: -0.1700
Data Index: 7010873 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.8398. Min Act: -0.1700
Data Index: 2601125 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.7773. Min Act: -0.1700
Data Index: 1467638 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.7773. Min Act: -0.1700
Data Index: 2231429 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.7773. Min Act: -0.1700
Data Index: 2232116 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.7148. Min Act: -0.1700
Data Index: 5436996 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.7148. Min Act: -0.1700
Data Index: 480444 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.6523. Min Act: -0.1700
Data Index: 8282010 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.6523. Min Act: -0.1700
Data Index: 537595 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.6523. Min Act: -0.1700
Data Index: 7357284 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.6523. Min Act: -0.1700
Data Index: 4681414 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.6523. Min Act: -0.1700
Data Index: 696874 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.5898. Min Act: -0.1700
Data Index: 3663857 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.5898. Min Act: -0.1700
Data Index: 570081 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.5898. Min Act: -0.1700
Data Index: 5255568 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9648. Min Range: -7.9648
Max Act: 7.5898. Min Act: -0.1700
Data Index: 6355281 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19