Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.6013. Min Act: -0.1700
Data Index: 5725761 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5388. Min Act: -0.1700
Data Index: 959407 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5388. Min Act: -0.1700
Data Index: 959406 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5388. Min Act: -0.1700
Data Index: 7657866 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5388. Min Act: -0.1700
Data Index: 2444868 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5075. Min Act: -0.1700
Data Index: 5438498 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5075. Min Act: -0.1700
Data Index: 7657863 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5075. Min Act: -0.1700
Data Index: 3999067 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.5388. Min Act: -0.1700
Data Index: 3371630 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4763. Min Act: -0.1700
Data Index: 3343103 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4450. Min Act: -0.1700
Data Index: 1921464 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4138. Min Act: -0.1700
Data Index: 5889759 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4138. Min Act: -0.1700
Data Index: 3536032 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3825. Min Act: -0.1700
Data Index: 2588385 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4450. Min Act: -0.1700
Data Index: 8400149 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3825. Min Act: -0.1700
Data Index: 665058 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4138. Min Act: -0.1700
Data Index: 5883534 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4138. Min Act: -0.1700
Data Index: 4772515 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3825. Min Act: -0.1700
Data Index: 6257473 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3825. Min Act: -0.1700
Data Index: 7110829 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19