Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4910 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.3322. Min Act: -0.1699
Data Index: 2759435 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.2697. Min Act: -0.1695
Data Index: 5831308 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.2697. Min Act: -0.1700
Data Index: 2173203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.2072. Min Act: -0.1700
Data Index: 6547676 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.2072. Min Act: -0.1698
Data Index: 855033 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.2072. Min Act: -0.1700
Data Index: 8543385 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 204157 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 1563913 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 678213 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 2642953 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 330594 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 2672789 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 2128340 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 344448 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 2754911 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 391339 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1689
Data Index: 2689205 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1692
Data Index: 2135163 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 1695597 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3322. Min Range: -7.3322
Max Act: 7.1447. Min Act: -0.1700
Data Index: 885047 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19