Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.8081. Min Act: -0.1700
Data Index: 5057242 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.7456. Min Act: -0.1700
Data Index: 5621065 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.6518. Min Act: -0.1700
Data Index: 4948071 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.6518. Min Act: -0.1700
Data Index: 6407225 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.5581. Min Act: -0.1700
Data Index: 6484200 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.5581. Min Act: -0.1700
Data Index: 6447509 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.5581. Min Act: -0.1700
Data Index: 773390 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.5268. Min Act: -0.1700
Data Index: 4425583 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4643. Min Act: -0.1700
Data Index: 6506009 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4331. Min Act: -0.1700
Data Index: 4948069 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4331. Min Act: -0.1700
Data Index: 7513997 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4331. Min Act: -0.1700
Data Index: 6611189 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4331. Min Act: -0.1700
Data Index: 6506008 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4331. Min Act: -0.1700
Data Index: 3383789 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4018. Min Act: -0.1700
Data Index: 190817 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.4018. Min Act: -0.1700
Data Index: 5701949 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.3706. Min Act: -0.1700
Data Index: 6506005 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.3081. Min Act: -0.1700
Data Index: 3823332 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.3081. Min Act: -0.1700
Data Index: 7025898 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8081. Min Range: -7.8081
Max Act: 7.3081. Min Act: -0.1700
Data Index: 5701947 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19