Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.6126. Min Act: -0.1700
Data Index: 67916 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.5188. Min Act: -0.1700
Data Index: 8493011 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.5501. Min Act: -0.1700
Data Index: 1661527 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.5188. Min Act: -0.1700
Data Index: 1531248 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.5188. Min Act: -0.1700
Data Index: 8015666 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.5188. Min Act: -0.1700
Data Index: 8705556 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.4876. Min Act: -0.1700
Data Index: 810891 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.4251. Min Act: -0.1700
Data Index: 1610106 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.3626. Min Act: -0.1700
Data Index: 3952284 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.3001. Min Act: -0.1700
Data Index: 1106689 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.2688. Min Act: -0.1700
Data Index: 2825450 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.2688. Min Act: -0.1700
Data Index: 1844869 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.2063. Min Act: -0.1700
Data Index: 2706771 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.1751. Min Act: -0.1700
Data Index: 4617735 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.1751. Min Act: -0.1700
Data Index: 4300322 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.2063. Min Act: -0.1700
Data Index: 7564405 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.1751. Min Act: -0.1700
Data Index: 4169710 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.1751. Min Act: -0.1700
Data Index: 7188205 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.1438. Min Act: -0.1700
Data Index: 125274 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6126. Min Range: -7.6126
Max Act: 7.1126. Min Act: -0.1700
Data Index: 4769419 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19