Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8378. Min Act: -0.1700
Data Index: 7072041 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8690. Min Act: -0.1700
Data Index: 2889914 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8065. Min Act: -0.1700
Data Index: 1700500 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7440. Min Act: -0.1700
Data Index: 8139474 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7128. Min Act: -0.1700
Data Index: 923506 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6815. Min Act: -0.1700
Data Index: 8158313 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7128. Min Act: -0.1700
Data Index: 8500694 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 6025340 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6190. Min Act: -0.1700
Data Index: 4383211 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5878. Min Act: -0.1700
Data Index: 2658316 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5878. Min Act: -0.1700
Data Index: 8264637 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6190. Min Act: -0.1700
Data Index: 6605552 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5878. Min Act: -0.1700
Data Index: 2227603 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5878. Min Act: -0.1700
Data Index: 3529033 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5878. Min Act: -0.1700
Data Index: 7907979 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5565. Min Act: -0.1700
Data Index: 8117114 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5565. Min Act: -0.1700
Data Index: 7986881 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5565. Min Act: -0.1700
Data Index: 1756961 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5565. Min Act: -0.1700
Data Index: 4510568 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5565. Min Act: -0.1700
Data Index: 6682626 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19