Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.9013. Min Act: -0.1700
Data Index: 6691678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8378. Min Act: -0.1700
Data Index: 1600152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8378. Min Act: -0.1700
Data Index: 4000142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8537. Min Act: -0.1700
Data Index: 3054672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8060. Min Act: -0.1700
Data Index: 2611719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8060. Min Act: -0.1700
Data Index: 2050891 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8060. Min Act: -0.1700
Data Index: 3855240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8060. Min Act: -0.1700
Data Index: 8719429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8060. Min Act: -0.1700
Data Index: 4551497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8219. Min Act: -0.1700
Data Index: 3184473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8060. Min Act: -0.1700
Data Index: 8203492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7900. Min Act: -0.1700
Data Index: 4711345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.8060. Min Act: -0.1700
Data Index: 394870 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7900. Min Act: -0.1700
Data Index: 1307213 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7900. Min Act: -0.1700
Data Index: 3761024 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7900. Min Act: -0.1700
Data Index: 2708791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7900. Min Act: -0.1700
Data Index: 8111648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7741. Min Act: -0.1700
Data Index: 5217652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7741. Min Act: -0.1700
Data Index: 5622157 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9013. Min Range: -2.9013
Max Act: 2.7741. Min Act: -0.1700
Data Index: 5700229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19