Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2157 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.7437. Min Act: -0.1700
Data Index: 8100816 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6812. Min Act: -0.1700
Data Index: 4347986 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6187. Min Act: -0.1699
Data Index: 863811 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6187. Min Act: -0.1700
Data Index: 8501741 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6187. Min Act: -0.1700
Data Index: 5689798 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6187. Min Act: -0.1700
Data Index: 1499576 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 6597724 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5875. Min Act: -0.1700
Data Index: 900392 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 1117248 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 783491 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 6747186 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5250. Min Act: -0.1700
Data Index: 768645 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5250. Min Act: -0.1700
Data Index: 2529987 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4625. Min Act: -0.1700
Data Index: 5560363 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4937. Min Act: -0.1700
Data Index: 5494311 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4937. Min Act: -0.1700
Data Index: 3479903 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4937. Min Act: -0.1700
Data Index: 902697 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4937. Min Act: -0.1700
Data Index: 3904377 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4937. Min Act: -0.1700
Data Index: 1886594 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4937. Min Act: -0.1700
Data Index: 3949168 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19