Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.6285. Min Act: -0.1700
Data Index: 738180 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.4097. Min Act: -0.1700
Data Index: 2499781 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.2847. Min Act: -0.1700
Data Index: 4728899 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.2535. Min Act: -0.1700
Data Index: 2605576 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.1597. Min Act: -0.1700
Data Index: 333134 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.1597. Min Act: -0.1700
Data Index: 2326532 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.0972. Min Act: -0.1700
Data Index: 5080344 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6285. Min Range: -6.6285
Max Act: 6.0035. Min Act: -0.1700
Data Index: 6288440 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.9410. Min Act: -0.1700
Data Index: 124672 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.9097. Min Act: -0.1700
Data Index: 4308523 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.8785. Min Act: -0.1700
Data Index: 5080348 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.9097. Min Act: -0.1700
Data Index: 6062728 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.8785. Min Act: -0.1700
Data Index: 5631703 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.8160. Min Act: -0.1700
Data Index: 2966041 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.8160. Min Act: -0.1700
Data Index: 4176294 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.8160. Min Act: -0.1700
Data Index: 2499777 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.8160. Min Act: -0.1700
Data Index: 2499778 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.7847. Min Act: -0.1700
Data Index: 730098 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.7535. Min Act: -0.1700
Data Index: 730097 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6285. Min Range: -6.6285
Max Act: 5.8160. Min Act: -0.1700
Data Index: 2692011 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19