Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1063. Min Range: -6.1063
Max Act: 6.1063. Min Act: -0.1700
Data Index: 4814526 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.9813. Min Act: -0.1700
Data Index: 5480995 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.9500. Min Act: -0.1700
Data Index: 3944806 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.8563. Min Act: -0.1700
Data Index: 2491350 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.8875. Min Act: -0.1700
Data Index: 5340576 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.8563. Min Act: -0.1700
Data Index: 7841459 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7938. Min Act: -0.1700
Data Index: 1152893 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7938. Min Act: -0.1700
Data Index: 5219209 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7625. Min Act: -0.1700
Data Index: 2374514 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7625. Min Act: -0.1700
Data Index: 1033480 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7625. Min Act: -0.1700
Data Index: 172703 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7938. Min Act: -0.1700
Data Index: 1748827 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7313. Min Act: -0.1700
Data Index: 5878649 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7313. Min Act: -0.1700
Data Index: 4563286 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7313. Min Act: -0.1700
Data Index: 6650643 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7313. Min Act: -0.1700
Data Index: 7702259 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7000. Min Act: -0.1700
Data Index: 5095454 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.7313. Min Act: -0.1700
Data Index: 8022113 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.6375. Min Act: -0.1700
Data Index: 6291754 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1063. Min Range: -6.1063
Max Act: 5.6375. Min Act: -0.1700
Data Index: 4907701 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19