Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2934. Min Range: -8.2934
Max Act: 8.2934. Min Act: -0.1700
Data Index: 5307011 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.6684. Min Act: -0.1700
Data Index: 5135347 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.6059. Min Act: -0.1700
Data Index: 3343831 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.5434. Min Act: -0.1700
Data Index: 2982378 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.4809. Min Act: -0.1700
Data Index: 6840304 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.5121. Min Act: -0.1700
Data Index: 3790748 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.4184. Min Act: -0.1700
Data Index: 4781692 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.4496. Min Act: -0.1700
Data Index: 8501222 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.4184. Min Act: -0.1700
Data Index: 1951467 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.4184. Min Act: -0.1700
Data Index: 706799 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.3559. Min Act: -0.1700
Data Index: 549511 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.3559. Min Act: -0.1700
Data Index: 1170057 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.3246. Min Act: -0.1700
Data Index: 3546122 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.3246. Min Act: -0.1700
Data Index: 8450990 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.2934. Min Act: -0.1700
Data Index: 5308771 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.2934. Min Act: -0.1700
Data Index: 4833361 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.2934. Min Act: -0.1700
Data Index: 4899374 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.1996. Min Act: -0.1700
Data Index: 4709563 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.1996. Min Act: -0.1700
Data Index: 5169184 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2934. Min Range: -8.2934
Max Act: 7.1371. Min Act: -0.1700
Data Index: 3512953 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19