Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2016. Min Range: -8.2016
Max Act: 8.2016. Min Act: -0.1700
Data Index: 4873409 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.6704. Min Act: -0.1700
Data Index: 3613956 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.5454. Min Act: -0.1700
Data Index: 102966 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.4516. Min Act: -0.1700
Data Index: 5802739 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.4204. Min Act: -0.1700
Data Index: 1574748 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.4204. Min Act: -0.1700
Data Index: 8547382 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.4204. Min Act: -0.1700
Data Index: 1574747 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.4204. Min Act: -0.1700
Data Index: 5802740 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.4204. Min Act: -0.1700
Data Index: 5858313 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.3891. Min Act: -0.1700
Data Index: 7250669 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.4204. Min Act: -0.1700
Data Index: 8353996 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.3891. Min Act: -0.1700
Data Index: 3158353 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.3266. Min Act: -0.1700
Data Index: 2877170 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.3579. Min Act: -0.1700
Data Index: 2852735 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.2954. Min Act: -0.1700
Data Index: 2721752 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.2954. Min Act: -0.1700
Data Index: 8155042 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.2641. Min Act: -0.1700
Data Index: 5441698 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.2641. Min Act: -0.1700
Data Index: 6842357 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.2641. Min Act: -0.1700
Data Index: 4738621 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2016. Min Range: -8.2016
Max Act: 7.2954. Min Act: -0.1700
Data Index: 264373 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19