Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5642 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.3482. Min Act: -0.1700
Data Index: 8168486 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2857. Min Act: -0.1700
Data Index: 3167435 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.2544. Min Act: -0.1700
Data Index: 4203794 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1700
Data Index: 966996 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.1607. Min Act: -0.1700
Data Index: 2539586 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0669. Min Act: -0.1700
Data Index: 4640397 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0669. Min Act: -0.1700
Data Index: 5494768 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0669. Min Act: -0.1700
Data Index: 152909 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0669. Min Act: -0.1700
Data Index: 5984743 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 2720863 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0044. Min Act: -0.1700
Data Index: 7488692 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 490659 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 8554435 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 5527139 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0357. Min Act: -0.1700
Data Index: 5944983 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0044. Min Act: -0.1700
Data Index: 6197676 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3482. Min Range: -5.3482
Max Act: 5.0044. Min Act: -0.1700
Data Index: 596967 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.9732. Min Act: -0.1700
Data Index: 3264714 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.9732. Min Act: -0.1700
Data Index: 1000404 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3482. Min Range: -5.3482
Max Act: 4.9732. Min Act: -0.1700
Data Index: 8061071 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19