Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5547 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2660. Min Range: -5.2660
Max Act: 5.2660. Min Act: -0.1700
Data Index: 7836854 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.8910. Min Act: -0.1700
Data Index: 1011113 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.8910. Min Act: -0.1700
Data Index: 1011115 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.7972. Min Act: -0.1700
Data Index: 4821846 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.7035. Min Act: -0.1700
Data Index: 7115821 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.6722. Min Act: -0.1700
Data Index: 3572908 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.6410. Min Act: -0.1700
Data Index: 2205760 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.6097. Min Act: -0.1700
Data Index: 3122171 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.6097. Min Act: -0.1700
Data Index: 8407486 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.5785. Min Act: -0.1700
Data Index: 766180 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.6097. Min Act: -0.1700
Data Index: 7269293 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.5785. Min Act: -0.1700
Data Index: 7487620 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.5785. Min Act: -0.1700
Data Index: 5055522 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.5472. Min Act: -0.1700
Data Index: 8230937 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.5472. Min Act: -0.1700
Data Index: 4239680 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.4847. Min Act: -0.1700
Data Index: 4239668 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.4847. Min Act: -0.1700
Data Index: 5773313 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.4847. Min Act: -0.1700
Data Index: 6429311 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.4847. Min Act: -0.1700
Data Index: 7354741 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2660. Min Range: -5.2660
Max Act: 4.4535. Min Act: -0.1700
Data Index: 643420 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19