Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 6907049 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 7529445 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1698
Data Index: 3535481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 4246645 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 2006947 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 176854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 1975306 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 6522389 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0908. Min Act: -0.1700
Data Index: 6257410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0596. Min Act: -0.1700
Data Index: 4854619 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0596. Min Act: -0.1700
Data Index: 4495404 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0596. Min Act: -0.1700
Data Index: 6055315 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0596. Min Act: -0.1700
Data Index: 704955 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0596. Min Act: -0.1700
Data Index: 8075444 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0596. Min Act: -0.1700
Data Index: 7870373 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0283. Min Act: -0.1700
Data Index: 171940 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0283. Min Act: -0.1700
Data Index: 56475 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0283. Min Act: -0.1700
Data Index: 5947692 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0283. Min Act: -0.1700
Data Index: 3613316 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0908. Min Range: -5.0908
Max Act: 5.0283. Min Act: -0.1700
Data Index: 2018671 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19