Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.5512. Min Act: -0.1700
Data Index: 14711 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.5027. Min Act: -0.1700
Data Index: 5255897 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.5027. Min Act: -0.1700
Data Index: 6042359 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.4702. Min Act: -0.1700
Data Index: 843203 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.4377. Min Act: -0.1700
Data Index: 229016 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.4377. Min Act: -0.1700
Data Index: 3594857 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.4540. Min Act: -0.1700
Data Index: 4400791 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.4377. Min Act: -0.1700
Data Index: 5229755 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3888. Min Act: -0.1700
Data Index: 282045 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.4051. Min Act: -0.1700
Data Index: 8390708 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.4214. Min Act: -0.1700
Data Index: 6406096 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3888. Min Act: -0.1700
Data Index: 3628171 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3725. Min Act: -0.1700
Data Index: 1316733 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3725. Min Act: -0.1700
Data Index: 4528678 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3888. Min Act: -0.1700
Data Index: 4258611 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3561. Min Act: -0.1700
Data Index: 4394165 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3725. Min Act: -0.1700
Data Index: 5688378 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3233. Min Act: -0.1700
Data Index: 2574175 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3397. Min Act: -0.1700
Data Index: 755909 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5512. Min Range: -2.5512
Max Act: 2.3397. Min Act: -0.1700
Data Index: 4913063 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19