Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.4989. Min Act: -0.1700
Data Index: 1734086 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.4364. Min Act: -0.1700
Data Index: 2109005 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.3739. Min Act: -0.1700
Data Index: 4616331 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.2489. Min Act: -0.1700
Data Index: 6026375 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.2489. Min Act: -0.1700
Data Index: 6366544 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.2489. Min Act: -0.1700
Data Index: 7139569 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.1864. Min Act: -0.1700
Data Index: 7189225 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.1864. Min Act: -0.1700
Data Index: 5122289 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.1239. Min Act: -0.1700
Data Index: 2457894 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.0614. Min Act: -0.1700
Data Index: 7277112 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.1239. Min Act: -0.1700
Data Index: 5068171 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.1239. Min Act: -0.1700
Data Index: 7969358 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.0614. Min Act: -0.1700
Data Index: 6825368 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.0614. Min Act: -0.1700
Data Index: 4947029 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.0614. Min Act: -0.1700
Data Index: 6109259 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.0614. Min Act: -0.1700
Data Index: 1280764 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.0301. Min Act: -0.1700
Data Index: 8546669 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4989. Min Range: -8.4989
Max Act: 8.0301. Min Act: -0.1700
Data Index: 4981443 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4989. Min Range: -8.4989
Max Act: 7.9989. Min Act: -0.1700
Data Index: 4695491 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4989. Min Range: -8.4989
Max Act: 7.9051. Min Act: -0.1700
Data Index: 6574763 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19