Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.5014. Min Act: -0.1700
Data Index: 794685 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.4389. Min Act: -0.1700
Data Index: 8714004 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 1223171 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 4093002 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1577. Min Act: -0.1700
Data Index: 1765671 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 1144379 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 7447020 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 4002163 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 7447017 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 3620287 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0014. Min Act: -0.1700
Data Index: 8604838 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0014. Min Act: -0.1700
Data Index: 3826597 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9702. Min Act: -0.1700
Data Index: 7788774 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9389. Min Act: -0.1700
Data Index: 6114278 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9702. Min Act: -0.1700
Data Index: 5129293 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0014. Min Act: -0.1700
Data Index: 5767839 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9077. Min Act: -0.1700
Data Index: 4712611 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9702. Min Act: -0.1700
Data Index: 8084262 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9077. Min Act: -0.1700
Data Index: 5527328 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9077. Min Act: -0.1700
Data Index: 312930 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19