Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.8717. Min Act: -0.1700
Data Index: 8149539 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.8092. Min Act: -0.1700
Data Index: 1651880 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.8717. Min Act: -0.1700
Data Index: 36377 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.7780. Min Act: -0.1700
Data Index: 8185359 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.7780. Min Act: -0.1700
Data Index: 1288059 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.7780. Min Act: -0.1700
Data Index: 5186173 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.7467. Min Act: -0.1700
Data Index: 1642893 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.7155. Min Act: -0.1700
Data Index: 2864552 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.6842. Min Act: -0.1700
Data Index: 4489855 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.6842. Min Act: -0.1700
Data Index: 6896628 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.6530. Min Act: -0.1700
Data Index: 3297457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.6530. Min Act: -0.1700
Data Index: 7407819 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.6530. Min Act: -0.1700
Data Index: 5835716 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.6530. Min Act: -0.1700
Data Index: 2654764 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.6217. Min Act: -0.1700
Data Index: 7739193 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.5905. Min Act: -0.1700
Data Index: 2584344 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5018587 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5282849 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.5905. Min Act: -0.1700
Data Index: 4346430 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8717. Min Range: -4.8717
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5440267 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19