Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.1590. Min Act: -0.1700
Data Index: 2849771 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.1118. Min Act: -0.1700
Data Index: 2739605 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.1118. Min Act: -0.1700
Data Index: 3190083 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0960. Min Act: -0.1700
Data Index: 8152869 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0802. Min Act: -0.1700
Data Index: 2477742 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0487. Min Act: -0.1700
Data Index: 486508 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0171. Min Act: -0.1700
Data Index: 2738843 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0329. Min Act: -0.1700
Data Index: 49051 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0329. Min Act: -0.1700
Data Index: 4568574 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0171. Min Act: -0.1700
Data Index: 857735 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9855. Min Act: -0.1700
Data Index: 5038038 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9855. Min Act: -0.1700
Data Index: 817683 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1590. Min Range: -3.1590
Max Act: 3.0013. Min Act: -0.1700
Data Index: 3209397 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9855. Min Act: -0.1700
Data Index: 7050062 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9855. Min Act: -0.1700
Data Index: 1221557 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9855. Min Act: -0.1700
Data Index: 2027286 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9539. Min Act: -0.1700
Data Index: 988045 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9697. Min Act: -0.1700
Data Index: 7333699 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9539. Min Act: -0.1700
Data Index: 4540062 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1590. Min Range: -3.1590
Max Act: 2.9539. Min Act: -0.1700
Data Index: 79883 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19