Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1394. Min Range: -6.1394
Max Act: 6.1394. Min Act: -0.1700
Data Index: 2258908 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1394. Min Range: -6.1394
Max Act: 6.0769. Min Act: -0.1700
Data Index: 8783409 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1394. Min Range: -6.1394
Max Act: 6.0144. Min Act: -0.1700
Data Index: 1211623 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.9832. Min Act: -0.1700
Data Index: 8780322 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.9207. Min Act: -0.1700
Data Index: 900711 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.9519. Min Act: -0.1700
Data Index: 8111776 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.9207. Min Act: -0.1700
Data Index: 8331938 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.9207. Min Act: -0.1700
Data Index: 2123083 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8894. Min Act: -0.1700
Data Index: 1327870 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8894. Min Act: -0.1700
Data Index: 6173959 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8894. Min Act: -0.1700
Data Index: 161145 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8894. Min Act: -0.1700
Data Index: 1446529 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8582. Min Act: -0.1700
Data Index: 1428914 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8582. Min Act: -0.1700
Data Index: 7952219 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8582. Min Act: -0.1700
Data Index: 6863116 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8582. Min Act: -0.1700
Data Index: 4145762 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8582. Min Act: -0.1700
Data Index: 2388529 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8582. Min Act: -0.1700
Data Index: 6764998 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8582. Min Act: -0.1700
Data Index: 4973888 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1394. Min Range: -6.1394
Max Act: 5.8269. Min Act: -0.1700
Data Index: 6065570 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19