Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8626. Min Act: -0.1700
Data Index: 5781229 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8626. Min Act: -0.1700
Data Index: 8552456 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8313. Min Act: -0.1700
Data Index: 5721496 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8313. Min Act: -0.1700
Data Index: 7712026 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8313. Min Act: -0.1700
Data Index: 5979639 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8001. Min Act: -0.1700
Data Index: 2355795 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8001. Min Act: -0.1700
Data Index: 7186694 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.8001. Min Act: -0.1700
Data Index: 390274 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7688. Min Act: -0.1700
Data Index: 8552453 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7688. Min Act: -0.1700
Data Index: 2097992 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7688. Min Act: -0.1700
Data Index: 8258896 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7376. Min Act: -0.1700
Data Index: 7850104 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7376. Min Act: -0.1700
Data Index: 558485 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7688. Min Act: -0.1700
Data Index: 560133 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7376. Min Act: -0.1700
Data Index: 8635681 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7376. Min Act: -0.1700
Data Index: 6984938 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7376. Min Act: -0.1700
Data Index: 2097986 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7376. Min Act: -0.1700
Data Index: 2019477 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7063. Min Act: -0.1700
Data Index: 1768250 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8626. Min Range: -4.8626
Max Act: 4.7063. Min Act: -0.1700
Data Index: 7447385 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19