Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.4178. Min Act: -0.1700
Data Index: 7747340 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2615. Min Act: -0.1700
Data Index: 6667963 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2615. Min Act: -0.1700
Data Index: 4385912 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2303. Min Act: -0.1700
Data Index: 127337 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1677. Min Act: -0.1700
Data Index: 1329838 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1052. Min Act: -0.1700
Data Index: 5199971 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1052. Min Act: -0.1700
Data Index: 5631951 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1052. Min Act: -0.1700
Data Index: 8106098 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1052. Min Act: -0.1700
Data Index: 2081339 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1052. Min Act: -0.1700
Data Index: 2995392 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1052. Min Act: -0.1700
Data Index: 2081337 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1052. Min Act: -0.1700
Data Index: 6152343 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0740. Min Act: -0.1700
Data Index: 5045063 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0740. Min Act: -0.1700
Data Index: 2203667 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0740. Min Act: -0.1700
Data Index: 2269760 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0427. Min Act: -0.1700
Data Index: 3573132 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0427. Min Act: -0.1700
Data Index: 5045068 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0427. Min Act: -0.1700
Data Index: 2203670 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0427. Min Act: -0.1700
Data Index: 1492815 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.0427. Min Act: -0.1700
Data Index: 5045065 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19