Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4663 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.9638. Min Act: -0.1700
Data Index: 358382 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.9638. Min Act: -0.1700
Data Index: 3877668 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.9326. Min Act: -0.1700
Data Index: 6458911 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.9013. Min Act: -0.1700
Data Index: 7767190 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.8700. Min Act: -0.1700
Data Index: 4273421 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.8388. Min Act: -0.1700
Data Index: 4127127 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.8388. Min Act: -0.1700
Data Index: 4012980 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.8075. Min Act: -0.1700
Data Index: 4304637 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7762. Min Act: -0.1700
Data Index: 1301279 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.8075. Min Act: -0.1700
Data Index: 6252356 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.8075. Min Act: -0.1700
Data Index: 202421 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7762. Min Act: -0.1700
Data Index: 3176281 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7762. Min Act: -0.1700
Data Index: 3567851 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7449. Min Act: -0.1700
Data Index: 2139072 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7449. Min Act: -0.1700
Data Index: 972317 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7449. Min Act: -0.1700
Data Index: 4389661 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7449. Min Act: -0.1700
Data Index: 6439351 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7449. Min Act: -0.1700
Data Index: 1887942 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7449. Min Act: -0.1700
Data Index: 2481230 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9638. Min Range: -3.9638
Max Act: 3.7137. Min Act: -0.1700
Data Index: 3353118 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19