Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1633. Min Range: -5.1633
Max Act: 5.1633. Min Act: -0.1700
Data Index: 4434930 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1633. Min Range: -5.1633
Max Act: 5.1008. Min Act: -0.1700
Data Index: 3259678 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1633. Min Range: -5.1633
Max Act: 5.0071. Min Act: -0.1700
Data Index: 5000794 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8821. Min Act: -0.1700
Data Index: 8671326 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8508. Min Act: -0.1700
Data Index: 2074931 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8508. Min Act: -0.1700
Data Index: 1956529 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8508. Min Act: -0.1700
Data Index: 7514774 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8508. Min Act: -0.1700
Data Index: 8261792 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8196. Min Act: -0.1700
Data Index: 510376 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8196. Min Act: -0.1700
Data Index: 3280011 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.8196. Min Act: -0.1700
Data Index: 1708859 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7571. Min Act: -0.1700
Data Index: 1403409 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7571. Min Act: -0.1700
Data Index: 6012175 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7571. Min Act: -0.1700
Data Index: 8499673 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7571. Min Act: -0.1700
Data Index: 6891005 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7258. Min Act: -0.1700
Data Index: 1914360 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7571. Min Act: -0.1700
Data Index: 3530530 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7571. Min Act: -0.1700
Data Index: 8334794 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7258. Min Act: -0.1700
Data Index: 8797368 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1633. Min Range: -5.1633
Max Act: 4.7571. Min Act: -0.1700
Data Index: 5042427 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19