Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5127 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4828. Min Act: -0.1700
Data Index: 603421 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4203. Min Act: -0.1700
Data Index: 3850140 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.3578. Min Act: -0.1700
Data Index: 7959729 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.3578. Min Act: -0.1700
Data Index: 5384147 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.3266. Min Act: -0.1700
Data Index: 4618787 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.2641. Min Act: -0.1700
Data Index: 2368513 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.2641. Min Act: -0.1700
Data Index: 6341089 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.2328. Min Act: -0.1700
Data Index: 1740521 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.2328. Min Act: -0.1700
Data Index: 3723699 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.2016. Min Act: -0.1700
Data Index: 7400004 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.2016. Min Act: -0.1700
Data Index: 5375132 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.2016. Min Act: -0.1700
Data Index: 6182205 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1703. Min Act: -0.1700
Data Index: 534393 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1703. Min Act: -0.1700
Data Index: 7513806 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1703. Min Act: -0.1700
Data Index: 6376375 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1703. Min Act: -0.1700
Data Index: 2203960 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1703. Min Act: -0.1700
Data Index: 593307 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1078. Min Act: -0.1700
Data Index: 8398237 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1391. Min Act: -0.1700
Data Index: 2121167 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.1391. Min Act: -0.1700
Data Index: 7631569 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19