Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4267 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.8306. Min Act: -0.1700
Data Index: 1730645 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.7681. Min Act: -0.1700
Data Index: 3369514 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.5806. Min Act: -0.1700
Data Index: 76981 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 7656021 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 1933169 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 1900264 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.4556. Min Act: -0.1700
Data Index: 3134647 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.3931. Min Act: -0.1700
Data Index: 1864965 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.3306. Min Act: -0.1700
Data Index: 2832701 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.2993. Min Act: -0.1700
Data Index: 6403379 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.2993. Min Act: -0.1700
Data Index: 6875200 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.2368. Min Act: -0.1700
Data Index: 6099076 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.2056. Min Act: -0.1700
Data Index: 3085839 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.2056. Min Act: -0.1700
Data Index: 3500436 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.2056. Min Act: -0.1700
Data Index: 41214 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.1431. Min Act: -0.1700
Data Index: 7719905 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.1743. Min Act: -0.1700
Data Index: 101567 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.1431. Min Act: -0.1700
Data Index: 8671893 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.1118. Min Act: -0.1700
Data Index: 89696 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8306. Min Range: -7.8306
Max Act: 7.0806. Min Act: -0.1700
Data Index: 4420817 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19