Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6282 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0572. Min Range: -6.0572
Max Act: 6.0572. Min Act: -0.1700
Data Index: 5005062 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0572. Min Range: -6.0572
Max Act: 6.0572. Min Act: -0.1700
Data Index: 7854635 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0572. Min Range: -6.0572
Max Act: 6.0572. Min Act: -0.1700
Data Index: 8311602 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.9947. Min Act: -0.1700
Data Index: 7854636 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.9947. Min Act: -0.1700
Data Index: 2809669 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.9322. Min Act: -0.1700
Data Index: 2809681 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.8385. Min Act: -0.1700
Data Index: 2809686 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.8072. Min Act: -0.1700
Data Index: 5092540 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.8072. Min Act: -0.1700
Data Index: 7854637 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.7760. Min Act: -0.1700
Data Index: 8827555 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.7447. Min Act: -0.1700
Data Index: 2809678 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.6822. Min Act: -0.1700
Data Index: 2809673 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.6822. Min Act: -0.1700
Data Index: 2809671 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.6822. Min Act: -0.1700
Data Index: 2809684 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.5885. Min Act: -0.1700
Data Index: 2809672 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.6197. Min Act: -0.1700
Data Index: 4487953 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.5885. Min Act: -0.1700
Data Index: 5149643 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.5885. Min Act: -0.1700
Data Index: 2332045 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.5572. Min Act: -0.1700
Data Index: 112677 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0572. Min Range: -6.0572
Max Act: 5.5572. Min Act: -0.1700
Data Index: 1664992 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19