Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0892. Min Range: -6.0892
Max Act: 6.0892. Min Act: -0.1700
Data Index: 7960484 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0892. Min Range: -6.0892
Max Act: 6.0580. Min Act: -0.1700
Data Index: 7286125 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.6517. Min Act: -0.1700
Data Index: 2290397 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.5267. Min Act: -0.1700
Data Index: 3845463 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4955. Min Act: -0.1700
Data Index: 5661530 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.5267. Min Act: -0.1700
Data Index: 2384469 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.5267. Min Act: -0.1700
Data Index: 6236704 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.5267. Min Act: -0.1700
Data Index: 6464089 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.5580. Min Act: -0.1700
Data Index: 5230124 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4955. Min Act: -0.1700
Data Index: 5724753 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4955. Min Act: -0.1700
Data Index: 993196 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4642. Min Act: -0.1700
Data Index: 4354248 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4642. Min Act: -0.1700
Data Index: 5183442 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4642. Min Act: -0.1700
Data Index: 656323 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4330. Min Act: -0.1700
Data Index: 118084 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4330. Min Act: -0.1700
Data Index: 5492139 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4330. Min Act: -0.1700
Data Index: 6732233 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4330. Min Act: -0.1700
Data Index: 5186825 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4330. Min Act: -0.1700
Data Index: 4715316 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0892. Min Range: -6.0892
Max Act: 5.4017. Min Act: -0.1700
Data Index: 2013588 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19