Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.3659. Min Act: -0.1700
Data Index: 4409639 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.3347. Min Act: -0.1700
Data Index: 4249534 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.3034. Min Act: -0.1700
Data Index: 2581441 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.2409. Min Act: -0.1700
Data Index: 2076572 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.2409. Min Act: -0.1700
Data Index: 4718706 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.2097. Min Act: -0.1699
Data Index: 999193 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.1472. Min Act: -0.1700
Data Index: 4866357 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.1159. Min Act: -0.1700
Data Index: 503522 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.1159. Min Act: -0.1700
Data Index: 3217382 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0847. Min Act: -0.1700
Data Index: 6191248 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0847. Min Act: -0.1700
Data Index: 5129749 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0534. Min Act: -0.1700
Data Index: 5128526 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0534. Min Act: -0.1700
Data Index: 1539818 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0847. Min Act: -0.1700
Data Index: 214830 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0534. Min Act: -0.1700
Data Index: 739131 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0534. Min Act: -0.1700
Data Index: 4227173 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0534. Min Act: -0.1700
Data Index: 12436 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0534. Min Act: -0.1700
Data Index: 3869430 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3659. Min Range: -6.3659
Max Act: 6.0222. Min Act: -0.1700
Data Index: 6652330 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3659. Min Range: -6.3659
Max Act: 5.9597. Min Act: -0.1700
Data Index: 6096931 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19