Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3155 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.4237. Min Act: -0.1700
Data Index: 7707672 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.2361. Min Act: -0.1700
Data Index: 3353160 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.2361. Min Act: -0.1700
Data Index: 7430325 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.2049. Min Act: -0.1700
Data Index: 1663717 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1736. Min Act: -0.1700
Data Index: 3145769 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.2361. Min Act: -0.1700
Data Index: 1125616 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.2049. Min Act: -0.1700
Data Index: 8743443 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.2049. Min Act: -0.1700
Data Index: 6005976 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1424. Min Act: -0.1700
Data Index: 4165180 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1424. Min Act: -0.1700
Data Index: 860921 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1736. Min Act: -0.1700
Data Index: 5505779 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1736. Min Act: -0.1700
Data Index: 7380158 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1424. Min Act: -0.1700
Data Index: 5860043 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1424. Min Act: -0.1700
Data Index: 6441786 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.0799. Min Act: -0.1700
Data Index: 7763458 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1111. Min Act: -0.1700
Data Index: 49700 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.1111. Min Act: -0.1700
Data Index: 3847098 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.0799. Min Act: -0.1700
Data Index: 3480606 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.0799. Min Act: -0.1700
Data Index: 6069481 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4237. Min Range: -4.4237
Max Act: 4.0486. Min Act: -0.1700
Data Index: 1130174 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19