Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1982 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1828. Min Range: -4.1828
Max Act: 4.1828. Min Act: -0.1700
Data Index: 3274437 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1828. Min Range: -4.1828
Max Act: 4.0265. Min Act: -0.1700
Data Index: 3689292 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.9640. Min Act: -0.1700
Data Index: 7167101 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.9327. Min Act: -0.1700
Data Index: 3328579 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.9014. Min Act: -0.1700
Data Index: 5246337 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.9014. Min Act: -0.1700
Data Index: 4041051 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.9014. Min Act: -0.1700
Data Index: 86895 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8702. Min Act: -0.1700
Data Index: 4374395 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8858. Min Act: -0.1700
Data Index: 813368 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8702. Min Act: -0.1700
Data Index: 4969319 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8545. Min Act: -0.1700
Data Index: 6998054 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8389. Min Act: -0.1700
Data Index: 6737571 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8545. Min Act: -0.1700
Data Index: 6257065 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8076. Min Act: -0.1700
Data Index: 2567338 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8076. Min Act: -0.1700
Data Index: 7808397 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8076. Min Act: -0.1700
Data Index: 741568 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.7920. Min Act: -0.1700
Data Index: 4678679 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.7920. Min Act: -0.1700
Data Index: 4225737 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.7920. Min Act: -0.1700
Data Index: 5577270 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1828. Min Range: -4.1828
Max Act: 3.8076. Min Act: -0.1700
Data Index: 3681196 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19