Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.9539. Min Act: -0.1700
Data Index: 6477414 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.8914. Min Act: -0.1700
Data Index: 4667527 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.7664. Min Act: -0.1700
Data Index: 5887569 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.8289. Min Act: -0.1700
Data Index: 5328740 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.7664. Min Act: -0.1700
Data Index: 1931385 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.7039. Min Act: -0.1700
Data Index: 1150393 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.8289. Min Act: -0.1700
Data Index: 4690722 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.7039. Min Act: -0.1700
Data Index: 6608452 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.7039. Min Act: -0.1700
Data Index: 176751 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.7039. Min Act: -0.1700
Data Index: 7825519 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 8487444 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 8066377 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 266312 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 4388055 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 1807621 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 4950642 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 445545 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 809684 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.6414. Min Act: -0.1700
Data Index: 5413570 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9539. Min Range: -7.9539
Max Act: 7.5789. Min Act: -0.1700
Data Index: 1712105 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19