Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.8164. Min Act: -0.1700
Data Index: 5744861 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.7852. Min Act: -0.1700
Data Index: 4117229 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5016800 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.6602. Min Act: -0.1700
Data Index: 5015140 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.6602. Min Act: -0.1700
Data Index: 1067837 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.5039. Min Act: -0.1700
Data Index: 8605353 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 3328645 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 2604062 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.5039. Min Act: -0.1700
Data Index: 1441245 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.5039. Min Act: -0.1700
Data Index: 5514617 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 1712794 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 7415690 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 2522379 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 8291234 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 8197067 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4414. Min Act: -0.1700
Data Index: 3813151 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4414. Min Act: -0.1700
Data Index: 6480921 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4102. Min Act: -0.1700
Data Index: 505410 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4414. Min Act: -0.1700
Data Index: 7333284 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8164. Min Range: -6.8164
Max Act: 6.4727. Min Act: -0.1700
Data Index: 5736677 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19