Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.4876. Min Act: -0.1700
Data Index: 1516437 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.1126. Min Act: -0.1700
Data Index: 8079852 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0501. Min Act: -0.1700
Data Index: 7483548 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0188. Min Act: -0.1700
Data Index: 1368457 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0188. Min Act: -0.1700
Data Index: 7151012 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.9563. Min Act: -0.1700
Data Index: 5438276 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.8001. Min Act: -0.1700
Data Index: 2141913 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.8001. Min Act: -0.1700
Data Index: 7408085 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.7688. Min Act: -0.1700
Data Index: 2141920 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.6751. Min Act: -0.1700
Data Index: 8768285 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.6126. Min Act: -0.1700
Data Index: 6282533 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.6126. Min Act: -0.1700
Data Index: 6535493 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.6126. Min Act: -0.1700
Data Index: 676528 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.6438. Min Act: -0.1700
Data Index: 4158089 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.5813. Min Act: -0.1700
Data Index: 852029 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.5501. Min Act: -0.1700
Data Index: 5973387 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.5188. Min Act: -0.1700
Data Index: 820404 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.4876. Min Act: -0.1700
Data Index: 4868132 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.4876. Min Act: -0.1700
Data Index: 1661439 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4876. Min Range: -7.4876
Max Act: 6.4876. Min Act: -0.1700
Data Index: 149099 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19