Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7433. Min Act: -0.1700
Data Index: 3310457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7120. Min Act: -0.1700
Data Index: 6427488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7120. Min Act: -0.1700
Data Index: 391977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7120. Min Act: -0.1700
Data Index: 2813103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7120. Min Act: -0.1700
Data Index: 945242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6807. Min Act: -0.1700
Data Index: 6095763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6807. Min Act: -0.1700
Data Index: 8194972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6807. Min Act: -0.1700
Data Index: 7952457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6807. Min Act: -0.1700
Data Index: 2497788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6494. Min Act: -0.1700
Data Index: 4811189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6807. Min Act: -0.1700
Data Index: 2840496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6494. Min Act: -0.1698
Data Index: 7983229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6494. Min Act: -0.1700
Data Index: 6140011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6181. Min Act: -0.1700
Data Index: 8642703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6181. Min Act: -0.1700
Data Index: 1653510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5868. Min Act: -0.1700
Data Index: 8672341 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5555. Min Act: -0.1700
Data Index: 2724997 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5555. Min Act: -0.1700
Data Index: 1503600 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 1438439 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 3953055 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19