Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4375 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.7055. Min Act: -0.1700
Data Index: 175546 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6743. Min Act: -0.1700
Data Index: 1419341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6743. Min Act: -0.1700
Data Index: 1195713 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6743. Min Act: -0.1700
Data Index: 2376318 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6430. Min Act: -0.1700
Data Index: 960162 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6430. Min Act: -0.1700
Data Index: 4211869 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6430. Min Act: -0.1700
Data Index: 7918757 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6430. Min Act: -0.1700
Data Index: 7918758 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6430. Min Act: -0.1700
Data Index: 1195714 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6430. Min Act: -0.1700
Data Index: 7892642 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 1808962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 3862246 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6430. Min Act: -0.1700
Data Index: 2455393 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 2474377 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 175545 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 2595775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 4218253 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 4471894 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 1365786 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7055. Min Range: -4.7055
Max Act: 4.6118. Min Act: -0.1700
Data Index: 4471897 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19