Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.1070. Min Act: -0.1700
Data Index: 3713843 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0758. Min Act: -0.1700
Data Index: 6627300 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0133. Min Act: -0.1700
Data Index: 6449380 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0133. Min Act: -0.1700
Data Index: 1718847 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0133. Min Act: -0.1700
Data Index: 12501 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0133. Min Act: -0.1700
Data Index: 3980910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9820. Min Act: -0.1700
Data Index: 6979633 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9820. Min Act: -0.1700
Data Index: 783805 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9820. Min Act: -0.1700
Data Index: 774057 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9820. Min Act: -0.1700
Data Index: 4696123 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 4187607 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 44597 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 3505490 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 5265690 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 5895060 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 3454917 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 3336849 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 6286467 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 979294 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9508. Min Act: -0.1700
Data Index: 2722384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19