Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.7975. Min Act: -0.1700
Data Index: 8690645 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.7350. Min Act: -0.1700
Data Index: 5340936 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.5475. Min Act: -0.1700
Data Index: 5486046 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.5475. Min Act: -0.1700
Data Index: 4683834 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4850. Min Act: -0.1700
Data Index: 6359272 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4537. Min Act: -0.1700
Data Index: 2628016 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4225. Min Act: -0.1700
Data Index: 5631927 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4537. Min Act: -0.1700
Data Index: 5331150 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4537. Min Act: -0.1700
Data Index: 1742329 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4225. Min Act: -0.1700
Data Index: 7626303 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3912. Min Act: -0.1700
Data Index: 7981207 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4225. Min Act: -0.1700
Data Index: 214969 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.4225. Min Act: -0.1700
Data Index: 283504 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3912. Min Act: -0.1700
Data Index: 3085113 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3600. Min Act: -0.1700
Data Index: 8182505 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3287. Min Act: -0.1700
Data Index: 970002 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3600. Min Act: -0.1700
Data Index: 2245784 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3287. Min Act: -0.1700
Data Index: 1709457 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3600. Min Act: -0.1700
Data Index: 4200585 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7975. Min Range: -5.7975
Max Act: 5.3287. Min Act: -0.1700
Data Index: 963009 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19