Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.6592. Min Act: -0.1700
Data Index: 746280 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.5967. Min Act: -0.1700
Data Index: 1924477 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.5342. Min Act: -0.1700
Data Index: 5899219 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4717. Min Act: -0.1700
Data Index: 1428322 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4717. Min Act: -0.1699
Data Index: 8044519 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4717. Min Act: -0.1700
Data Index: 345689 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4717. Min Act: -0.1700
Data Index: 1741731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4717. Min Act: -0.1700
Data Index: 5243971 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 1820442 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 6126643 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 3701092 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 2734659 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 450758 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 1938330 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 7733424 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 3033982 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 376751 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 3527549 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 542191 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6592. Min Range: -6.6592
Max Act: 6.4092. Min Act: -0.1700
Data Index: 2531304 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19