Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.7734. Min Act: -0.1700
Data Index: 8261874 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.7415. Min Act: -0.1700
Data Index: 6389119 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.7256. Min Act: -0.1700
Data Index: 8083099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.7415. Min Act: -0.1700
Data Index: 464569 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6936. Min Act: -0.1700
Data Index: 6075296 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6936. Min Act: -0.1700
Data Index: 4515384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6936. Min Act: -0.1700
Data Index: 6703007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6936. Min Act: -0.1700
Data Index: 87414 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6294. Min Act: -0.1700
Data Index: 1396213 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6133. Min Act: -0.1700
Data Index: 833339 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6133. Min Act: -0.1700
Data Index: 1752428 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6294. Min Act: -0.1700
Data Index: 8010906 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6133. Min Act: -0.1700
Data Index: 7337006 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6133. Min Act: -0.1700
Data Index: 7654614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6133. Min Act: -0.1700
Data Index: 19637 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.5973. Min Act: -0.1700
Data Index: 8796725 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.5973. Min Act: -0.1700
Data Index: 4446664 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.5812. Min Act: -0.1700
Data Index: 474285 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.6133. Min Act: -0.1700
Data Index: 3091361 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7734. Min Range: -2.7734
Max Act: 2.5973. Min Act: -0.1700
Data Index: 726532 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19