Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1408 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.4680. Min Act: -0.1700
Data Index: 7606643 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.3430. Min Act: -0.1700
Data Index: 4325781 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.3430. Min Act: -0.1700
Data Index: 8737528 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.2493. Min Act: -0.1700
Data Index: 775339 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.2180. Min Act: -0.1700
Data Index: 5757005 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.2180. Min Act: -0.1700
Data Index: 5562419 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1868. Min Act: -0.1700
Data Index: 3808724 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1555. Min Act: -0.1700
Data Index: 4187016 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1555. Min Act: -0.1700
Data Index: 2595795 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1555. Min Act: -0.1700
Data Index: 5149982 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1555. Min Act: -0.1700
Data Index: 8264253 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1555. Min Act: -0.1700
Data Index: 84723 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1243. Min Act: -0.1700
Data Index: 1399770 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1243. Min Act: -0.1700
Data Index: 6268478 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.1243. Min Act: -0.1700
Data Index: 1709578 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.0930. Min Act: -0.1700
Data Index: 3434699 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.0930. Min Act: -0.1700
Data Index: 1902282 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.0930. Min Act: -0.1700
Data Index: 3566636 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.0930. Min Act: -0.1700
Data Index: 3642582 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4680. Min Range: -5.4680
Max Act: 5.0930. Min Act: -0.1700
Data Index: 2941245 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19