Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0401. Min Range: -5.0401
Max Act: 5.0401. Min Act: -0.1700
Data Index: 6511047 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0401. Min Range: -5.0401
Max Act: 5.0089. Min Act: -0.1700
Data Index: 4680085 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.7901. Min Act: -0.1700
Data Index: 4375863 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.7276. Min Act: -0.1700
Data Index: 8170975 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.6651. Min Act: -0.1700
Data Index: 8279195 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.6651. Min Act: -0.1700
Data Index: 3823534 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.6339. Min Act: -0.1700
Data Index: 8248894 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.6339. Min Act: -0.1700
Data Index: 7569785 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.6026. Min Act: -0.1700
Data Index: 3823535 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.6026. Min Act: -0.1700
Data Index: 3624312 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5714. Min Act: -0.1700
Data Index: 2972709 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5089. Min Act: -0.1700
Data Index: 7684676 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5401. Min Act: -0.1700
Data Index: 4919469 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5089. Min Act: -0.1700
Data Index: 3458520 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5089. Min Act: -0.1700
Data Index: 3823533 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5401. Min Act: -0.1700
Data Index: 6060395 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5401. Min Act: -0.1700
Data Index: 8595567 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5089. Min Act: -0.1700
Data Index: 7645767 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.5089. Min Act: -0.1700
Data Index: 145515 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.4776. Min Act: -0.1700
Data Index: 333764 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19