Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.9063. Min Act: -0.1700
Data Index: 3856975 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.8438. Min Act: -0.1700
Data Index: 1577090 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.7813. Min Act: -0.1700
Data Index: 4985730 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.5938. Min Act: -0.1700
Data Index: 3032569 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.5313. Min Act: -0.1700
Data Index: 554721 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.4063. Min Act: -0.1700
Data Index: 3595585 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.4063. Min Act: -0.1700
Data Index: 1254503 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.2813. Min Act: -0.1700
Data Index: 2089299 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.2501. Min Act: -0.1700
Data Index: 6407677 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.2501. Min Act: -0.1700
Data Index: 3630605 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.2501. Min Act: -0.1700
Data Index: 305088 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.2188. Min Act: -0.1700
Data Index: 1391006 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.2501. Min Act: -0.1700
Data Index: 6399935 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.1876. Min Act: -0.1700
Data Index: 244306 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.1876. Min Act: -0.1700
Data Index: 2684875 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.1251. Min Act: -0.1700
Data Index: 1137543 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.0626. Min Act: -0.1700
Data Index: 7475811 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9063. Min Range: -7.9063
Max Act: 7.0626. Min Act: -0.1700
Data Index: 4290577 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9063. Min Range: -7.9063
Max Act: 6.9688. Min Act: -0.1700
Data Index: 696322 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9063. Min Range: -7.9063
Max Act: 6.9688. Min Act: -0.1700
Data Index: 2566588 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19