Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3742. Min Act: -0.1700
Data Index: 2345808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3742. Min Act: -0.1700
Data Index: 461229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 1827569 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 8096405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 12878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 3266085 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 7124079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 3001993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 1393942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 420845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3430. Min Act: -0.1700
Data Index: 4725339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 2982644 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 5191359 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 3390128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 2496791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 7205590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 2147489 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 764189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.3117. Min Act: -0.1700
Data Index: 3334667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3742. Min Range: -4.3742
Max Act: 4.2804. Min Act: -0.1700
Data Index: 1236921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19