Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6262. Min Range: -5.6262
Max Act: 5.6262. Min Act: -0.1700
Data Index: 7639126 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6262. Min Range: -5.6262
Max Act: 5.2199. Min Act: -0.1700
Data Index: 4038024 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6262. Min Range: -5.6262
Max Act: 5.1887. Min Act: -0.1700
Data Index: 3854321 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6262. Min Range: -5.6262
Max Act: 5.0324. Min Act: -0.1700
Data Index: 639541 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.9699. Min Act: -0.1700
Data Index: 8407144 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8762. Min Act: -0.1700
Data Index: 5482450 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.9074. Min Act: -0.1700
Data Index: 1338027 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8762. Min Act: -0.1700
Data Index: 111037 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8449. Min Act: -0.1700
Data Index: 2746164 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8449. Min Act: -0.1700
Data Index: 6563229 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8449. Min Act: -0.1700
Data Index: 4160013 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8762. Min Act: -0.1700
Data Index: 5536775 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8449. Min Act: -0.1700
Data Index: 8391038 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8137. Min Act: -0.1700
Data Index: 4717801 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8137. Min Act: -0.1700
Data Index: 1815140 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.8449. Min Act: -0.1700
Data Index: 7196732 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.7824. Min Act: -0.1700
Data Index: 6869125 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.7824. Min Act: -0.1700
Data Index: 8300685 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.7512. Min Act: -0.1700
Data Index: 540872 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6262. Min Range: -5.6262
Max Act: 4.7512. Min Act: -0.1700
Data Index: 8103171 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19