Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5674 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.3012. Min Act: -0.1700
Data Index: 8442832 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.3012. Min Act: -0.1700
Data Index: 6454133 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.3012. Min Act: -0.1700
Data Index: 751607 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.1762. Min Act: -0.1700
Data Index: 1521593 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.1762. Min Act: -0.1700
Data Index: 8546331 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.1762. Min Act: -0.1700
Data Index: 1547513 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.1762. Min Act: -0.1700
Data Index: 1567094 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.1762. Min Act: -0.1700
Data Index: 4007469 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.1762. Min Act: -0.1700
Data Index: 4242339 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 5390024 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 3017102 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.3012. Min Range: -17.3012
Max Act: 16.9262. Min Act: -0.1700
Data Index: 5263455 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 6875597 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 6746323 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 2417201 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 3831721 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 6215269 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 134469 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.3012. Min Range: -17.3012
Max Act: 17.0512. Min Act: -0.1700
Data Index: 1237568 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.3012. Min Range: -17.3012
Max Act: 16.9262. Min Act: -0.1700
Data Index: 5762595 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19