Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1686. Min Range: -8.1686
Max Act: 8.1686. Min Act: -0.1700
Data Index: 2596898 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1686. Min Range: -8.1686
Max Act: 8.1061. Min Act: -0.1700
Data Index: 4281652 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.9811. Min Act: -0.1700
Data Index: 2723569 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.9811. Min Act: -0.1700
Data Index: 350293 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.9186. Min Act: -0.1700
Data Index: 6728817 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.9186. Min Act: -0.1700
Data Index: 5311648 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.7936. Min Act: -0.1700
Data Index: 6067344 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.7311. Min Act: -0.1700
Data Index: 8382978 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.7311. Min Act: -0.1700
Data Index: 4328065 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.6998. Min Act: -0.1700
Data Index: 5416752 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.6998. Min Act: -0.1700
Data Index: 8043440 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.6373. Min Act: -0.1700
Data Index: 8196143 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.6061. Min Act: -0.1700
Data Index: 7403676 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.6061. Min Act: -0.1700
Data Index: 3146272 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.5748. Min Act: -0.1700
Data Index: 751544 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.5436. Min Act: -0.1700
Data Index: 6766062 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.5436. Min Act: -0.1700
Data Index: 4215453 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.5436. Min Act: -0.1700
Data Index: 5667614 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.5436. Min Act: -0.1700
Data Index: 209856 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1686. Min Range: -8.1686
Max Act: 7.5123. Min Act: -0.1700
Data Index: 2162661 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19