Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5692 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.6864. Min Act: -0.1700
Data Index: 987925 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.4989. Min Act: -0.1700
Data Index: 6497141 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.4676. Min Act: -0.1700
Data Index: 2501965 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.4051. Min Act: -0.1700
Data Index: 6401319 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.3426. Min Act: -0.1700
Data Index: 8756954 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.3739. Min Act: -0.1700
Data Index: 8506376 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.2801. Min Act: -0.1700
Data Index: 7459172 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.2801. Min Act: -0.1700
Data Index: 6835026 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.2489. Min Act: -0.1700
Data Index: 1479625 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.2489. Min Act: -0.1700
Data Index: 4815869 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.1864. Min Act: -0.1700
Data Index: 6602513 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.1239. Min Act: -0.1700
Data Index: 2398536 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.1551. Min Act: -0.1700
Data Index: 342871 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.1551. Min Act: -0.1700
Data Index: 459780 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.1239. Min Act: -0.1700
Data Index: 6597931 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.1239. Min Act: -0.1700
Data Index: 5698879 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.0614. Min Act: -0.1700
Data Index: 56356 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.0614. Min Act: -0.1700
Data Index: 1933956 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6864. Min Range: -6.6864
Max Act: 6.0614. Min Act: -0.1700
Data Index: 3552155 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6864. Min Range: -6.6864
Max Act: 5.9989. Min Act: -0.1700
Data Index: 3645203 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19