Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1538. Min Range: -6.1538
Max Act: 6.1538. Min Act: -0.1700
Data Index: 84498 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1538. Min Range: -6.1538
Max Act: 6.0913. Min Act: -0.1700
Data Index: 8545073 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.7475. Min Act: -0.1700
Data Index: 3917829 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.7475. Min Act: -0.1700
Data Index: 7818154 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.7475. Min Act: -0.1700
Data Index: 7301434 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.6225. Min Act: -0.1700
Data Index: 7889645 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.6850. Min Act: -0.1700
Data Index: 6308415 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.6225. Min Act: -0.1700
Data Index: 8223145 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.6225. Min Act: -0.1700
Data Index: 6198313 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.5913. Min Act: -0.1700
Data Index: 485134 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.5600. Min Act: -0.1700
Data Index: 5630851 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.5600. Min Act: -0.1700
Data Index: 7579037 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.5600. Min Act: -0.1700
Data Index: 5615860 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.5288. Min Act: -0.1700
Data Index: 251818 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.4975. Min Act: -0.1700
Data Index: 334158 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.5288. Min Act: -0.1700
Data Index: 8347226 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.4975. Min Act: -0.1700
Data Index: 3787752 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.4663. Min Act: -0.1700
Data Index: 6451813 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.4350. Min Act: -0.1700
Data Index: 6326381 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1538. Min Range: -6.1538
Max Act: 5.4350. Min Act: -0.1700
Data Index: 5647209 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19