Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5024 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.5030. Min Act: -0.1700
Data Index: 994712 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.4405. Min Act: -0.1700
Data Index: 5857909 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.4405. Min Act: -0.1700
Data Index: 1083858 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3780. Min Act: -0.1700
Data Index: 3443710 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3780. Min Act: -0.1700
Data Index: 8469287 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3155. Min Act: -0.1700
Data Index: 7596787 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3780. Min Act: -0.1700
Data Index: 6353728 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3780. Min Act: -0.1700
Data Index: 5988736 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.2530. Min Act: -0.1700
Data Index: 2529185 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3155. Min Act: -0.1700
Data Index: 8044442 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3155. Min Act: -0.1700
Data Index: 3303990 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3155. Min Act: -0.1700
Data Index: 4622143 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3155. Min Act: -0.1700
Data Index: 900739 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3155. Min Act: -0.1700
Data Index: 3423571 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.3155. Min Act: -0.1700
Data Index: 3535689 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.2530. Min Act: -0.1700
Data Index: 5138846 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.2530. Min Act: -0.1700
Data Index: 5552024 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.2530. Min Act: -0.1700
Data Index: 3403493 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.2530. Min Act: -0.1700
Data Index: 5600487 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5030. Min Range: -7.5030
Max Act: 7.2530. Min Act: -0.1700
Data Index: 1280780 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19