Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5313 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.7856. Min Act: -0.1700
Data Index: 399329 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.4419. Min Act: -0.1700
Data Index: 831687 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.3481. Min Act: -0.1700
Data Index: 3154483 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.3481. Min Act: -0.1700
Data Index: 7386746 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.3169. Min Act: -0.1700
Data Index: 4555203 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.3169. Min Act: -0.1700
Data Index: 2075475 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.2856. Min Act: -0.1700
Data Index: 7268926 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.2544. Min Act: -0.1700
Data Index: 4542166 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.2231. Min Act: -0.1700
Data Index: 5002542 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.2231. Min Act: -0.1700
Data Index: 2929842 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.2231. Min Act: -0.1700
Data Index: 4483699 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.1919. Min Act: -0.1700
Data Index: 5751378 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.2231. Min Act: -0.1700
Data Index: 206306 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.1294. Min Act: -0.1700
Data Index: 2307769 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.1606. Min Act: -0.1700
Data Index: 2633234 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.1606. Min Act: -0.1700
Data Index: 1870419 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.1294. Min Act: -0.1700
Data Index: 8208022 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.1294. Min Act: -0.1700
Data Index: 1240489 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.0669. Min Act: -0.1700
Data Index: 4549675 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7856. Min Range: -5.7856
Max Act: 5.0669. Min Act: -0.1700
Data Index: 17108 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19