Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4055 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3383. Min Range: -6.3383
Max Act: 6.3383. Min Act: -0.1700
Data Index: 2926714 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3383. Min Range: -6.3383
Max Act: 6.2133. Min Act: -0.1700
Data Index: 4165464 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3383. Min Range: -6.3383
Max Act: 6.1508. Min Act: -0.1700
Data Index: 4622170 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3383. Min Range: -6.3383
Max Act: 6.0883. Min Act: -0.1700
Data Index: 5484297 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3383. Min Range: -6.3383
Max Act: 6.0258. Min Act: -0.1700
Data Index: 7405972 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3383. Min Range: -6.3383
Max Act: 6.0258. Min Act: -0.1700
Data Index: 7645447 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9946. Min Act: -0.1700
Data Index: 6700979 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9946. Min Act: -0.1700
Data Index: 767821 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9633. Min Act: -0.1700
Data Index: 164640 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9633. Min Act: -0.1700
Data Index: 1976009 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9633. Min Act: -0.1700
Data Index: 8824042 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9321. Min Act: -0.1700
Data Index: 4824704 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9008. Min Act: -0.1700
Data Index: 1496858 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.9008. Min Act: -0.1700
Data Index: 4600952 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.8696. Min Act: -0.1700
Data Index: 2400840 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.8383. Min Act: -0.1700
Data Index: 3012898 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.8071. Min Act: -0.1700
Data Index: 2927002 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.8383. Min Act: -0.1700
Data Index: 5983607 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.8696. Min Act: -0.1700
Data Index: 8389356 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3383. Min Range: -6.3383
Max Act: 5.8071. Min Act: -0.1700
Data Index: 2335509 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19