Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5925 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.5645. Min Act: -0.1700
Data Index: 2464041 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.5020. Min Act: -0.1700
Data Index: 1330726 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.2520. Min Act: -0.1700
Data Index: 3055965 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.2520. Min Act: -0.1700
Data Index: 2712820 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.2520. Min Act: -0.1700
Data Index: 6686426 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.1895. Min Act: -0.1700
Data Index: 8716836 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.1895. Min Act: -0.1700
Data Index: 6482905 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.1270. Min Act: -0.1700
Data Index: 3427988 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.1582. Min Act: -0.1700
Data Index: 8716813 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.1582. Min Act: -0.1700
Data Index: 7956261 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.1270. Min Act: -0.1700
Data Index: 1230390 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.0957. Min Act: -0.1700
Data Index: 810180 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.0957. Min Act: -0.1700
Data Index: 4877862 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.0957. Min Act: -0.1700
Data Index: 483247 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.0645. Min Act: -0.1700
Data Index: 8565331 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.0645. Min Act: -0.1700
Data Index: 4877861 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5645. Min Range: -5.5645
Max Act: 5.0020. Min Act: -0.1700
Data Index: 5561949 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5645. Min Range: -5.5645
Max Act: 4.9707. Min Act: -0.1700
Data Index: 7026286 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5645. Min Range: -5.5645
Max Act: 4.9707. Min Act: -0.1700
Data Index: 8636206 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5645. Min Range: -5.5645
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1714266 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19