Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 509 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1428. Min Range: -3.1428
Max Act: 3.1428. Min Act: -0.1700
Data Index: 2510960 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1428. Min Range: -3.1428
Max Act: 3.0955. Min Act: -0.1700
Data Index: 3547789 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1428. Min Range: -3.1428
Max Act: 3.0798. Min Act: -0.1700
Data Index: 4854117 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1428. Min Range: -3.1428
Max Act: 3.0324. Min Act: -0.1700
Data Index: 1289427 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1428. Min Range: -3.1428
Max Act: 3.0324. Min Act: -0.1700
Data Index: 5984202 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1428. Min Range: -3.1428
Max Act: 3.0324. Min Act: -0.1700
Data Index: 8362704 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9850. Min Act: -0.1700
Data Index: 4629435 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9850. Min Act: -0.1700
Data Index: 6716 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9850. Min Act: -0.1700
Data Index: 3854398 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1428. Min Range: -3.1428
Max Act: 3.0008. Min Act: -0.1700
Data Index: 8243837 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9534. Min Act: -0.1700
Data Index: 2563680 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9534. Min Act: -0.1700
Data Index: 6537588 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9692. Min Act: -0.1700
Data Index: 6897779 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9534. Min Act: -0.1700
Data Index: 3566969 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9692. Min Act: -0.1700
Data Index: 1438752 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9692. Min Act: -0.1700
Data Index: 5451062 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9534. Min Act: -0.1700
Data Index: 1625431 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9692. Min Act: -0.1700
Data Index: 1673856 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9534. Min Act: -0.1700
Data Index: 8693637 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1428. Min Range: -3.1428
Max Act: 2.9534. Min Act: -0.1700
Data Index: 7446181 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19