Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2003. Min Range: -4.2003
Max Act: 4.2003. Min Act: -0.1700
Data Index: 7016088 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.9815. Min Act: -0.1700
Data Index: 4855497 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.9502. Min Act: -0.1700
Data Index: 2969622 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.8877. Min Act: -0.1700
Data Index: 8652617 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.8564. Min Act: -0.1700
Data Index: 6954159 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.8095. Min Act: -0.1700
Data Index: 8381488 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.8095. Min Act: -0.1700
Data Index: 483807 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.7626. Min Act: -0.1700
Data Index: 6057861 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.7470. Min Act: -0.1700
Data Index: 1051800 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.7313. Min Act: -0.1700
Data Index: 8347180 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.6531. Min Act: -0.1700
Data Index: 6478348 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.6531. Min Act: -0.1700
Data Index: 8482879 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.6218. Min Act: -0.1700
Data Index: 4203679 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.6062. Min Act: -0.1700
Data Index: 630131 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.6062. Min Act: -0.1700
Data Index: 3349386 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.6218. Min Act: -0.1700
Data Index: 4746858 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.5905. Min Act: -0.1700
Data Index: 35119 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.5905. Min Act: -0.1700
Data Index: 2410528 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.5749. Min Act: -0.1700
Data Index: 1129681 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2003. Min Range: -4.2003
Max Act: 3.5122. Min Act: -0.1700
Data Index: 4627675 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19