Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0281. Min Range: -6.0281
Max Act: 6.0281. Min Act: -0.1700
Data Index: 8358705 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.9969. Min Act: -0.1700
Data Index: 5827365 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.9656. Min Act: -0.1700
Data Index: 3142439 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.9656. Min Act: -0.1700
Data Index: 7680892 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.9344. Min Act: -0.1700
Data Index: 3772434 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.9031. Min Act: -0.1700
Data Index: 6703205 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8719. Min Act: -0.1700
Data Index: 5678118 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8719. Min Act: -0.1700
Data Index: 8220719 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8719. Min Act: -0.1700
Data Index: 7530007 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8719. Min Act: -0.1700
Data Index: 5828606 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8719. Min Act: -0.1700
Data Index: 1729857 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8719. Min Act: -0.1700
Data Index: 3739959 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8719. Min Act: -0.1700
Data Index: 3528769 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.9031. Min Act: -0.1700
Data Index: 3255428 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8406. Min Act: -0.1700
Data Index: 6634926 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8406. Min Act: -0.1700
Data Index: 6710858 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8094. Min Act: -0.1700
Data Index: 673457 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8094. Min Act: -0.1700
Data Index: 5137318 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8406. Min Act: -0.1700
Data Index: 4105528 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0281. Min Range: -6.0281
Max Act: 5.8406. Min Act: -0.1700
Data Index: 8363301 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19