Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5220 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6404. Min Range: -9.6404
Max Act: 9.6404. Min Act: -0.1700
Data Index: 6979695 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6404. Min Range: -9.6404
Max Act: 9.0154. Min Act: -0.1700
Data Index: 5984036 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6404. Min Range: -9.6404
Max Act: 9.0154. Min Act: -0.1700
Data Index: 64302 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.9529. Min Act: -0.1700
Data Index: 2560515 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.9529. Min Act: -0.1700
Data Index: 4963670 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.9529. Min Act: -0.1700
Data Index: 3835105 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.8904. Min Act: -0.1700
Data Index: 1296161 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.8279. Min Act: -0.1700
Data Index: 721251 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.7654. Min Act: -0.1700
Data Index: 5794933 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.7654. Min Act: -0.1700
Data Index: 1883100 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.8279. Min Act: -0.1700
Data Index: 1645864 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.7654. Min Act: -0.1700
Data Index: 7676256 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.7654. Min Act: -0.1700
Data Index: 1507608 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.7654. Min Act: -0.1700
Data Index: 6866049 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.7654. Min Act: -0.1700
Data Index: 5012355 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.7029. Min Act: -0.1700
Data Index: 905509 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.6404. Min Act: -0.1700
Data Index: 7782891 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.6404. Min Act: -0.1700
Data Index: 512855 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.6404. Min Act: -0.1700
Data Index: 8175813 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6404. Min Range: -9.6404
Max Act: 8.6404. Min Act: -0.1700
Data Index: 7670921 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19