Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1333 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.9788. Min Act: -0.1700
Data Index: 8331694 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.9163. Min Act: -0.1700
Data Index: 4350483 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.9163. Min Act: -0.1700
Data Index: 4059061 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.8850. Min Act: -0.1700
Data Index: 5744935 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.9163. Min Act: -0.1700
Data Index: 7506196 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.8225. Min Act: -0.1700
Data Index: 109450 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.8225. Min Act: -0.1700
Data Index: 2164597 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.8225. Min Act: -0.1700
Data Index: 386811 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.8538. Min Act: -0.1700
Data Index: 5178076 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7913. Min Act: -0.1700
Data Index: 7124013 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7913. Min Act: -0.1700
Data Index: 6811694 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7600. Min Act: -0.1700
Data Index: 1293949 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7600. Min Act: -0.1700
Data Index: 3331979 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7600. Min Act: -0.1700
Data Index: 1598882 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7288. Min Act: -0.1700
Data Index: 4209492 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7288. Min Act: -0.1700
Data Index: 7124015 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7288. Min Act: -0.1700
Data Index: 4305981 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7288. Min Act: -0.1700
Data Index: 109451 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7288. Min Act: -0.1700
Data Index: 6550296 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9788. Min Range: -5.9788
Max Act: 5.7600. Min Act: -0.1700
Data Index: 1037720 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19