Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2390. Min Range: -6.2390
Max Act: 6.2390. Min Act: -0.1700
Data Index: 4066554 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2390. Min Range: -6.2390
Max Act: 6.0828. Min Act: -0.1700
Data Index: 86343 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2390. Min Range: -6.2390
Max Act: 6.0515. Min Act: -0.1700
Data Index: 2651361 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2390. Min Range: -6.2390
Max Act: 6.0515. Min Act: -0.1700
Data Index: 7435215 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.9265. Min Act: -0.1700
Data Index: 2664360 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3083475 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8640. Min Act: -0.1700
Data Index: 1009530 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8640. Min Act: -0.1700
Data Index: 5608439 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8640. Min Act: -0.1700
Data Index: 6913133 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8640. Min Act: -0.1700
Data Index: 7518342 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8640. Min Act: -0.1700
Data Index: 3083469 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8328. Min Act: -0.1700
Data Index: 1009520 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8328. Min Act: -0.1700
Data Index: 6817941 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8015. Min Act: -0.1700
Data Index: 4881476 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8015. Min Act: -0.1700
Data Index: 5093534 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8015. Min Act: -0.1700
Data Index: 3868869 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8015. Min Act: -0.1700
Data Index: 1102778 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.7703. Min Act: -0.1700
Data Index: 3823787 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.8015. Min Act: -0.1700
Data Index: 5954647 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2390. Min Range: -6.2390
Max Act: 5.7703. Min Act: -0.1700
Data Index: 618020 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19