Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.6030. Min Act: -0.1700
Data Index: 6972791 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5718. Min Act: -0.1700
Data Index: 3205281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5718. Min Act: -0.1700
Data Index: 6106387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5718. Min Act: -0.1700
Data Index: 7336035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 5011399 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 2483940 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 6851851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 6038752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 5978044 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 5660866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 5378462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 5026356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 1476755 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 4989744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 4688242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 1202438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 3777867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 3734878 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 244742 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6030. Min Range: -4.6030
Max Act: 4.5405. Min Act: -0.1700
Data Index: 791257 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19