Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4166 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.1145. Min Act: -0.1700
Data Index: 2725822 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.0832. Min Act: -0.1696
Data Index: 4719877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.0520. Min Act: -0.1700
Data Index: 5087382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.0520. Min Act: -0.1700
Data Index: 2811781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.0207. Min Act: -0.1700
Data Index: 6408973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9895. Min Act: -0.1700
Data Index: 1311780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9895. Min Act: -0.1700
Data Index: 1358024 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9895. Min Act: -0.1700
Data Index: 5535011 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9895. Min Act: -0.1700
Data Index: 6158107 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9895. Min Act: -0.1700
Data Index: 6249828 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9270. Min Act: -0.1700
Data Index: 7449381 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1700
Data Index: 4037746 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1699
Data Index: 7252570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1700
Data Index: 1156374 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1700
Data Index: 7097535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1696
Data Index: 5000710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1700
Data Index: 2617951 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9895. Min Act: -0.1700
Data Index: 6146908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1700
Data Index: 5260681 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1700
Data Index: 5235863 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19