Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2080 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.5454. Min Act: -0.1700
Data Index: 6931870 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.3892. Min Act: -0.1700
Data Index: 6185612 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.3267. Min Act: -0.1700
Data Index: 5518295 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.2954. Min Act: -0.1700
Data Index: 3837172 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.2642. Min Act: -0.1700
Data Index: 7510578 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.1704. Min Act: -0.1700
Data Index: 7326422 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.1392. Min Act: -0.1700
Data Index: 3804074 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.1704. Min Act: -0.1700
Data Index: 5616538 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.0767. Min Act: -0.1700
Data Index: 6937376 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.0767. Min Act: -0.1700
Data Index: 4613502 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.0454. Min Act: -0.1700
Data Index: 6223550 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.0454. Min Act: -0.1700
Data Index: 7344448 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5454. Min Range: -6.5454
Max Act: 6.0454. Min Act: -0.1700
Data Index: 6544022 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5454. Min Range: -6.5454
Max Act: 5.9829. Min Act: -0.1700
Data Index: 659102 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5454. Min Range: -6.5454
Max Act: 5.9829. Min Act: -0.1700
Data Index: 7195829 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5454. Min Range: -6.5454
Max Act: 5.9517. Min Act: -0.1700
Data Index: 7707210 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5454. Min Range: -6.5454
Max Act: 5.9517. Min Act: -0.1700
Data Index: 802779 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5454. Min Range: -6.5454
Max Act: 5.9204. Min Act: -0.1700
Data Index: 5741103 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5454. Min Range: -6.5454
Max Act: 5.8892. Min Act: -0.1700
Data Index: 4440180 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5454. Min Range: -6.5454
Max Act: 5.9204. Min Act: -0.1700
Data Index: 6577219 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19