Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2810 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0075. Min Range: -4.0075
Max Act: 4.0075. Min Act: -0.1700
Data Index: 7080114 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9450. Min Act: -0.1700
Data Index: 1333302 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9450. Min Act: -0.1700
Data Index: 8509453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9137. Min Act: -0.1700
Data Index: 7412753 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9450. Min Act: -0.1700
Data Index: 7137105 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9137. Min Act: -0.1700
Data Index: 70149 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9137. Min Act: -0.1700
Data Index: 7869834 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9137. Min Act: -0.1700
Data Index: 7238347 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9137. Min Act: -0.1700
Data Index: 6906171 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9137. Min Act: -0.1700
Data Index: 7996185 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 6631347 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 3869499 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 7454603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 7673436 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 5167112 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 7673437 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.9137. Min Act: -0.1700
Data Index: 5326717 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 5346701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 1098602 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0075. Min Range: -4.0075
Max Act: 3.8824. Min Act: -0.1700
Data Index: 5366937 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19