Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 614 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.3555. Min Act: -0.1700
Data Index: 6174239 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.2930. Min Act: -0.1700
Data Index: 2673906 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.2305. Min Act: -0.1700
Data Index: 7214942 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.2305. Min Act: -0.1700
Data Index: 5154292 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1680. Min Act: -0.1700
Data Index: 3380479 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1993. Min Act: -0.1700
Data Index: 1465287 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1993. Min Act: -0.1700
Data Index: 4943789 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.2305. Min Act: -0.1700
Data Index: 7605190 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1680. Min Act: -0.1700
Data Index: 3933764 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1680. Min Act: -0.1700
Data Index: 5714176 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1993. Min Act: -0.1700
Data Index: 3133786 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1680. Min Act: -0.1700
Data Index: 3105373 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1368. Min Act: -0.1700
Data Index: 3491286 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1368. Min Act: -0.1700
Data Index: 5416626 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.0430. Min Act: -0.1700
Data Index: 5239720 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.0743. Min Act: -0.1700
Data Index: 72307 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.1055. Min Act: -0.1700
Data Index: 6758052 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.0430. Min Act: -0.1700
Data Index: 7163526 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.0430. Min Act: -0.1700
Data Index: 2728166 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3555. Min Range: -5.3555
Max Act: 5.0430. Min Act: -0.1700
Data Index: 792838 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19