Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1827 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.8274. Min Act: -0.1700
Data Index: 7192529 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.5149. Min Act: -0.1700
Data Index: 1434381 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.4524. Min Act: -0.1700
Data Index: 5546243 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.4212. Min Act: -0.1700
Data Index: 7147886 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.4212. Min Act: -0.1700
Data Index: 1239850 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.4212. Min Act: -0.1700
Data Index: 4506769 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.4212. Min Act: -0.1700
Data Index: 2151387 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.3274. Min Act: -0.1700
Data Index: 963139 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.2962. Min Act: -0.1700
Data Index: 6095670 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.2649. Min Act: -0.1700
Data Index: 836526 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.2337. Min Act: -0.1700
Data Index: 2345263 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.2337. Min Act: -0.1700
Data Index: 5253786 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.1712. Min Act: -0.1700
Data Index: 3257542 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.1712. Min Act: -0.1700
Data Index: 8444391 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.1712. Min Act: -0.1700
Data Index: 333652 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.1712. Min Act: -0.1700
Data Index: 931027 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.0774. Min Act: -0.1700
Data Index: 3723783 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.0774. Min Act: -0.1700
Data Index: 2715043 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.1087. Min Act: -0.1700
Data Index: 8220149 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8274. Min Range: -7.8274
Max Act: 7.0774. Min Act: -0.1700
Data Index: 6827749 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19