Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.8969. Min Act: -0.1700
Data Index: 954798 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.5844. Min Act: -0.1700
Data Index: 5270008 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4594. Min Act: -0.1700
Data Index: 5530533 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.4281. Min Act: -0.1700
Data Index: 4566748 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.3344. Min Act: -0.1700
Data Index: 2631247 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.2094. Min Act: -0.1700
Data Index: 8138341 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.1469. Min Act: -0.1700
Data Index: 182261 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.0844. Min Act: -0.1700
Data Index: 4304002 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.0844. Min Act: -0.1700
Data Index: 3477477 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.1156. Min Act: -0.1700
Data Index: 7004212 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.0844. Min Act: -0.1700
Data Index: 7692734 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.0531. Min Act: -0.1700
Data Index: 6981430 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8969. Min Range: -7.8969
Max Act: 6.9906. Min Act: -0.1700
Data Index: 2794796 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.0219. Min Act: -0.1700
Data Index: 1367 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8969. Min Range: -7.8969
Max Act: 7.0219. Min Act: -0.1700
Data Index: 3343591 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8969. Min Range: -7.8969
Max Act: 6.9594. Min Act: -0.1700
Data Index: 276113 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8969. Min Range: -7.8969
Max Act: 6.9906. Min Act: -0.1700
Data Index: 3838283 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8969. Min Range: -7.8969
Max Act: 6.9906. Min Act: -0.1700
Data Index: 8198954 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8969. Min Range: -7.8969
Max Act: 6.9594. Min Act: -0.1700
Data Index: 2114824 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8969. Min Range: -7.8969
Max Act: 6.9594. Min Act: -0.1700
Data Index: 565757 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19