Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3745. Min Range: -8.3745
Max Act: 8.3745. Min Act: -0.1700
Data Index: 6076080 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3745. Min Range: -8.3745
Max Act: 8.2495. Min Act: -0.1700
Data Index: 4008198 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3745. Min Range: -8.3745
Max Act: 8.1870. Min Act: -0.1700
Data Index: 4366604 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3745. Min Range: -8.3745
Max Act: 8.1245. Min Act: -0.1700
Data Index: 8026646 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3745. Min Range: -8.3745
Max Act: 8.0620. Min Act: -0.1700
Data Index: 6411526 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.9370. Min Act: -0.1700
Data Index: 3493385 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.8745. Min Act: -0.1700
Data Index: 2774891 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.8745. Min Act: -0.1700
Data Index: 1199497 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.7808. Min Act: -0.1700
Data Index: 1080568 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.7808. Min Act: -0.1700
Data Index: 3718641 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.8120. Min Act: -0.1700
Data Index: 1783959 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.7808. Min Act: -0.1700
Data Index: 6454551 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.6870. Min Act: -0.1700
Data Index: 1167561 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.6870. Min Act: -0.1700
Data Index: 1074825 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.7808. Min Act: -0.1700
Data Index: 4007724 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.7495. Min Act: -0.1700
Data Index: 6192483 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.7495. Min Act: -0.1700
Data Index: 3483590 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.7808. Min Act: -0.1700
Data Index: 4220953 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.6870. Min Act: -0.1700
Data Index: 104462 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3745. Min Range: -8.3745
Max Act: 7.6558. Min Act: -0.1700
Data Index: 2246588 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19