Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7718. Min Range: -6.7718
Max Act: 6.7718. Min Act: -0.1700
Data Index: 6709457 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7718. Min Range: -6.7718
Max Act: 6.6468. Min Act: -0.1700
Data Index: 5014003 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7718. Min Range: -6.7718
Max Act: 6.4280. Min Act: -0.1700
Data Index: 8763545 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7718. Min Range: -6.7718
Max Act: 6.0843. Min Act: -0.1700
Data Index: 3505841 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7718. Min Range: -6.7718
Max Act: 6.0530. Min Act: -0.1700
Data Index: 6084064 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7718. Min Range: -6.7718
Max Act: 6.0843. Min Act: -0.1700
Data Index: 58899 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.9593. Min Act: -0.1700
Data Index: 6782624 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.9593. Min Act: -0.1699
Data Index: 7813158 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8655. Min Act: -0.1698
Data Index: 6625435 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8030. Min Act: -0.1700
Data Index: 2014611 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8343. Min Act: -0.1699
Data Index: 1585399 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8343. Min Act: -0.1700
Data Index: 6860096 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8030. Min Act: -0.1697
Data Index: 1808223 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8030. Min Act: -0.1700
Data Index: 655193 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8030. Min Act: -0.1700
Data Index: 4320902 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.8343. Min Act: -0.1700
Data Index: 6942219 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.7718. Min Act: -0.1700
Data Index: 8569621 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.7405. Min Act: -0.1700
Data Index: 4015504 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.7405. Min Act: -0.1700
Data Index: 3724844 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7718. Min Range: -6.7718
Max Act: 5.7093. Min Act: -0.1700
Data Index: 3941992 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19