Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.1454. Min Act: -0.1700
Data Index: 7213345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.1141. Min Act: -0.1700
Data Index: 1337942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.0516. Min Act: -0.1700
Data Index: 7499598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.0204. Min Act: -0.1700
Data Index: 3838047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.0204. Min Act: -0.1700
Data Index: 3572750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.0204. Min Act: -0.1700
Data Index: 8553803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.0204. Min Act: -0.1700
Data Index: 6611866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9891. Min Act: -0.1700
Data Index: 3192597 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9891. Min Act: -0.1700
Data Index: 3488682 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9891. Min Act: -0.1700
Data Index: 7017267 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9891. Min Act: -0.1700
Data Index: 7847071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 631879 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 8192481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 6968744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 1705701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 346891 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 7251371 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 810469 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 6162538 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9578. Min Act: -0.1700
Data Index: 4094500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19