Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.7134. Min Act: -0.1700
Data Index: 3692993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.7134. Min Act: -0.1700
Data Index: 2423241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.7134. Min Act: -0.1700
Data Index: 4851332 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.7134. Min Act: -0.1700
Data Index: 7950774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6822. Min Act: -0.1700
Data Index: 1843276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6822. Min Act: -0.1700
Data Index: 2803385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6822. Min Act: -0.1700
Data Index: 4509627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6822. Min Act: -0.1700
Data Index: 8826202 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6822. Min Act: -0.1700
Data Index: 8114175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6822. Min Act: -0.1700
Data Index: 5771810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6822. Min Act: -0.1700
Data Index: 231583 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6509. Min Act: -0.1700
Data Index: 3676715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6196. Min Act: -0.1700
Data Index: 7093420 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6509. Min Act: -0.1700
Data Index: 5515794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6509. Min Act: -0.1700
Data Index: 1446204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6509. Min Act: -0.1700
Data Index: 445946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6509. Min Act: -0.1700
Data Index: 2145496 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6196. Min Act: -0.1700
Data Index: 293977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6196. Min Act: -0.1700
Data Index: 3114074 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7134. Min Range: -3.7134
Max Act: 3.6196. Min Act: -0.1700
Data Index: 3243998 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19