Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2701 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0005. Min Range: -9.0005
Max Act: 9.0005. Min Act: -0.1700
Data Index: 8401880 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.7505. Min Act: -0.1700
Data Index: 3956274 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.7505. Min Act: -0.1700
Data Index: 1608542 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.6880. Min Act: -0.1700
Data Index: 8328009 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.6880. Min Act: -0.1700
Data Index: 3298874 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.6880. Min Act: -0.1700
Data Index: 2294191 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.6255. Min Act: -0.1700
Data Index: 1608556 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.6255. Min Act: -0.1700
Data Index: 1608541 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.6255. Min Act: -0.1700
Data Index: 2294190 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.6255. Min Act: -0.1700
Data Index: 1608547 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5630. Min Act: -0.1700
Data Index: 1608543 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5630. Min Act: -0.1700
Data Index: 6761768 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 1608545 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 4117506 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 1819630 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 61257 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 5151512 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 1608537 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 251621 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0005. Min Range: -9.0005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 1608544 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19