Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0787. Min Range: -5.0787
Max Act: 5.0787. Min Act: -0.1700
Data Index: 2753845 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.9849. Min Act: -0.1700
Data Index: 6648587 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.9849. Min Act: -0.1700
Data Index: 1552103 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.9224. Min Act: -0.1700
Data Index: 4698796 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.8599. Min Act: -0.1700
Data Index: 4475890 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.8912. Min Act: -0.1700
Data Index: 1105152 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.8599. Min Act: -0.1700
Data Index: 7892427 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.8287. Min Act: -0.1700
Data Index: 4694504 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.8287. Min Act: -0.1700
Data Index: 3737265 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.8287. Min Act: -0.1700
Data Index: 7910800 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.7037. Min Act: -0.1700
Data Index: 3991730 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6724. Min Act: -0.1700
Data Index: 3247054 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.7037. Min Act: -0.1700
Data Index: 1406829 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6724. Min Act: -0.1700
Data Index: 2318334 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5879560 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5613364 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5674833 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6412. Min Act: -0.1700
Data Index: 3622588 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6724. Min Act: -0.1700
Data Index: 4171425 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0787. Min Range: -5.0787
Max Act: 4.6412. Min Act: -0.1700
Data Index: 3032833 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19