Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1014. Min Range: -4.1014
Max Act: 4.1014. Min Act: -0.1700
Data Index: 4341976 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1014. Min Range: -4.1014
Max Act: 4.0389. Min Act: -0.1700
Data Index: 4940669 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1014. Min Range: -4.1014
Max Act: 4.0389. Min Act: -0.1700
Data Index: 7973328 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1014. Min Range: -4.1014
Max Act: 4.0077. Min Act: -0.1700
Data Index: 2585615 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1014. Min Range: -4.1014
Max Act: 4.0077. Min Act: -0.1700
Data Index: 4155663 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9764. Min Act: -0.1700
Data Index: 6272595 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9451. Min Act: -0.1700
Data Index: 6169152 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9764. Min Act: -0.1700
Data Index: 4155664 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9451. Min Act: -0.1700
Data Index: 6306469 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9139. Min Act: -0.1700
Data Index: 8328968 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9764. Min Act: -0.1700
Data Index: 7111873 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9139. Min Act: -0.1700
Data Index: 6866409 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.9139. Min Act: -0.1700
Data Index: 8680037 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.8826. Min Act: -0.1700
Data Index: 3608436 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.8513. Min Act: -0.1700
Data Index: 7794410 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.8826. Min Act: -0.1700
Data Index: 3535861 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.8826. Min Act: -0.1700
Data Index: 8348131 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.8513. Min Act: -0.1700
Data Index: 7352793 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.8513. Min Act: -0.1700
Data Index: 6167962 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1014. Min Range: -4.1014
Max Act: 3.8513. Min Act: -0.1700
Data Index: 1884616 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19