Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.6506. Min Act: -0.1700
Data Index: 3662573 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.6506. Min Act: -0.1700
Data Index: 8560675 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3694. Min Act: -0.1700
Data Index: 1964573 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.3694. Min Act: -0.1700
Data Index: 497487 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2756. Min Act: -0.1700
Data Index: 8171232 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2756. Min Act: -0.1700
Data Index: 1508825 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2756. Min Act: -0.1700
Data Index: 1835864 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2444. Min Act: -0.1700
Data Index: 6772043 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.2131. Min Act: -0.1700
Data Index: 2595663 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.1819. Min Act: -0.1700
Data Index: 3364246 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.1819. Min Act: -0.1700
Data Index: 3599846 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.1506. Min Act: -0.1700
Data Index: 8686779 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.1193. Min Act: -0.1700
Data Index: 3564994 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.1193. Min Act: -0.1700
Data Index: 7334004 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.1193. Min Act: -0.1700
Data Index: 4937989 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 1586832 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 943008 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.1193. Min Act: -0.1700
Data Index: 1289815 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 5736299 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6506. Min Range: -4.6506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 7516645 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19