Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.2580. Min Act: -0.1700
Data Index: 81885 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.2415. Min Act: -0.1700
Data Index: 947593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.2415. Min Act: -0.1700
Data Index: 8722890 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1918. Min Act: -0.1700
Data Index: 459884 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1918. Min Act: -0.1700
Data Index: 3384231 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1751. Min Act: -0.1700
Data Index: 4529312 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1918. Min Act: -0.1700
Data Index: 1845898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 8445664 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 4635414 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 1756828 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 3706472 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 2072920 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 1160980 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 7380298 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 7371429 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 2901289 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 7274902 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1251. Min Act: -0.1700
Data Index: 3546086 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1418. Min Act: -0.1700
Data Index: 3761912 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2580. Min Range: -2.2580
Max Act: 2.1585. Min Act: -0.1700
Data Index: 1468251 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19