Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0721. Min Range: -8.0721
Max Act: 8.0721. Min Act: -0.1700
Data Index: 8554962 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.8221. Min Act: -0.1700
Data Index: 1272434 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.6971. Min Act: -0.1700
Data Index: 6818877 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.6346. Min Act: -0.1700
Data Index: 5061962 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.5721. Min Act: -0.1700
Data Index: 3640108 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.5409. Min Act: -0.1700
Data Index: 6945187 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.5096. Min Act: -0.1700
Data Index: 8554961 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.4159. Min Act: -0.1700
Data Index: 6945186 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.4159. Min Act: -0.1700
Data Index: 8223162 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3846. Min Act: -0.1700
Data Index: 8554963 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3846. Min Act: -0.1700
Data Index: 8415196 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3221. Min Act: -0.1700
Data Index: 4808287 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3534. Min Act: -0.1700
Data Index: 8156366 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3534. Min Act: -0.1700
Data Index: 3640106 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3221. Min Act: -0.1700
Data Index: 8556082 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3221. Min Act: -0.1700
Data Index: 6804205 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.3221. Min Act: -0.1700
Data Index: 6804222 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.2909. Min Act: -0.1700
Data Index: 5991560 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.2909. Min Act: -0.1700
Data Index: 1272435 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0721. Min Range: -8.0721
Max Act: 7.2596. Min Act: -0.1700
Data Index: 3721312 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19