Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1788 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.8313. Min Act: -0.1700
Data Index: 753079 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.7376. Min Act: -0.1700
Data Index: 5317873 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.6126. Min Act: -0.1700
Data Index: 5882391 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.6438. Min Act: -0.1700
Data Index: 7011346 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.5501. Min Act: -0.1700
Data Index: 2481372 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.5501. Min Act: -0.1700
Data Index: 3385586 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.5501. Min Act: -0.1700
Data Index: 8593674 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.5188. Min Act: -0.1700
Data Index: 5995340 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.5188. Min Act: -0.1700
Data Index: 573640 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.5501. Min Act: -0.1700
Data Index: 4331023 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.4876. Min Act: -0.1700
Data Index: 2427184 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.5501. Min Act: -0.1700
Data Index: 1655406 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.4876. Min Act: -0.1700
Data Index: 3593899 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.4876. Min Act: -0.1700
Data Index: 1966786 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.4251. Min Act: -0.1700
Data Index: 1325659 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.4563. Min Act: -0.1700
Data Index: 4487780 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.3938. Min Act: -0.1700
Data Index: 4492668 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.4251. Min Act: -0.1700
Data Index: 2263981 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.3938. Min Act: -0.1700
Data Index: 853477 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8313. Min Range: -5.8313
Max Act: 5.3938. Min Act: -0.1700
Data Index: 8666646 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19