Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4261 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.8390. Min Act: -0.1700
Data Index: 125277 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.8390. Min Act: -0.1700
Data Index: 2100014 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.8077. Min Act: -0.1700
Data Index: 520131 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.6827. Min Act: -0.1700
Data Index: 4520297 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.6827. Min Act: -0.1700
Data Index: 2099950 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.6202. Min Act: -0.1700
Data Index: 4496434 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.6202. Min Act: -0.1700
Data Index: 4504321 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.5577. Min Act: -0.1700
Data Index: 4399625 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.5265. Min Act: -0.1700
Data Index: 7055774 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.4952. Min Act: -0.1700
Data Index: 6795720 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.4952. Min Act: -0.1700
Data Index: 2667801 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.4952. Min Act: -0.1700
Data Index: 8607774 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3702. Min Act: -0.1700
Data Index: 4317097 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3702. Min Act: -0.1700
Data Index: 7892489 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3390. Min Act: -0.1700
Data Index: 894256 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3077. Min Act: -0.1700
Data Index: 2231512 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3702. Min Act: -0.1700
Data Index: 2675565 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3390. Min Act: -0.1700
Data Index: 7651557 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3077. Min Act: -0.1700
Data Index: 7855847 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8390. Min Range: -5.8390
Max Act: 5.3077. Min Act: -0.1700
Data Index: 8353724 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19