Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 165 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.1551. Min Act: -0.1700
Data Index: 7365656 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.1864. Min Act: -0.1700
Data Index: 281820 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.1239. Min Act: -0.1700
Data Index: 1551751 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.0926. Min Act: -0.1700
Data Index: 4450709 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.0926. Min Act: -0.1700
Data Index: 6920200 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.0614. Min Act: -0.1700
Data Index: 2256959 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.0614. Min Act: -0.1700
Data Index: 3767011 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1864. Min Range: -5.1864
Max Act: 5.0614. Min Act: -0.1700
Data Index: 8775444 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.9989. Min Act: -0.1700
Data Index: 701470 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.9676. Min Act: -0.1700
Data Index: 802304 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.9364. Min Act: -0.1700
Data Index: 1794223 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.9051. Min Act: -0.1700
Data Index: 4745404 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8739. Min Act: -0.1700
Data Index: 8790891 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8739. Min Act: -0.1700
Data Index: 3210263 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8426. Min Act: -0.1700
Data Index: 5043937 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2867642 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8426. Min Act: -0.1700
Data Index: 6558230 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8426. Min Act: -0.1700
Data Index: 7738873 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8114. Min Act: -0.1700
Data Index: 5808092 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1864. Min Range: -5.1864
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2863310 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19