Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2335 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.8798. Min Act: -0.1700
Data Index: 2809407 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.7236. Min Act: -0.1700
Data Index: 7180639 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.6923. Min Act: -0.1700
Data Index: 557314 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.5986. Min Act: -0.1700
Data Index: 145934 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.5361. Min Act: -0.1700
Data Index: 3524642 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.4736. Min Act: -0.1700
Data Index: 2696870 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.5048. Min Act: -0.1700
Data Index: 5929318 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.4423. Min Act: -0.1700
Data Index: 1804751 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.3798. Min Act: -0.1700
Data Index: 7977920 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.3173. Min Act: -0.1700
Data Index: 8569692 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2861. Min Act: -0.1700
Data Index: 4488442 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2861. Min Act: -0.1700
Data Index: 6177266 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2861. Min Act: -0.1700
Data Index: 7680011 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2548. Min Act: -0.1700
Data Index: 7021379 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2548. Min Act: -0.1700
Data Index: 958915 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4257535 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4420519 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2236. Min Act: -0.1700
Data Index: 1237869 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.1923. Min Act: -0.1700
Data Index: 1027905 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8798. Min Range: -6.8798
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4708153 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19