Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5196 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1906. Min Range: -5.1906
Max Act: 5.1906. Min Act: -0.1700
Data Index: 6489950 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1906. Min Range: -5.1906
Max Act: 5.1281. Min Act: -0.1700
Data Index: 488036 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1906. Min Range: -5.1906
Max Act: 5.0343. Min Act: -0.1700
Data Index: 5245578 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1906. Min Range: -5.1906
Max Act: 5.0031. Min Act: -0.1700
Data Index: 8314470 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.9718. Min Act: -0.1700
Data Index: 1690103 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.9718. Min Act: -0.1700
Data Index: 7546759 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.9718. Min Act: -0.1700
Data Index: 5000763 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.9093. Min Act: -0.1700
Data Index: 2583063 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8468. Min Act: -0.1700
Data Index: 897950 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8781. Min Act: -0.1700
Data Index: 5167073 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8781. Min Act: -0.1700
Data Index: 5419677 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8156. Min Act: -0.1700
Data Index: 454068 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.8156. Min Act: -0.1700
Data Index: 2672920 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7843. Min Act: -0.1700
Data Index: 5214444 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7531. Min Act: -0.1700
Data Index: 8354679 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7531. Min Act: -0.1700
Data Index: 2458825 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7843. Min Act: -0.1700
Data Index: 3032841 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7218. Min Act: -0.1700
Data Index: 5345014 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7218. Min Act: -0.1700
Data Index: 2339452 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1906. Min Range: -5.1906
Max Act: 4.7218. Min Act: -0.1700
Data Index: 3706859 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19