Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0718. Min Range: -4.0718
Max Act: 4.0718. Min Act: -0.1700
Data Index: 1373743 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.9780. Min Act: -0.1700
Data Index: 2609489 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.9155. Min Act: -0.1700
Data Index: 2366786 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.8842. Min Act: -0.1700
Data Index: 3495410 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.8842. Min Act: -0.1700
Data Index: 3614583 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.8217. Min Act: -0.1700
Data Index: 3581202 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.7591. Min Act: -0.1700
Data Index: 8447410 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.7591. Min Act: -0.1700
Data Index: 3210855 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.7278. Min Act: -0.1700
Data Index: 8090693 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.7278. Min Act: -0.1700
Data Index: 3398841 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6652. Min Act: -0.1700
Data Index: 1813290 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6652. Min Act: -0.1700
Data Index: 1094931 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6652. Min Act: -0.1700
Data Index: 138843 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6027. Min Act: -0.1700
Data Index: 2349530 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6027. Min Act: -0.1700
Data Index: 3315501 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6027. Min Act: -0.1700
Data Index: 3398836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.5713. Min Act: -0.1700
Data Index: 1552782 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6340. Min Act: -0.1700
Data Index: 2044643 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6027. Min Act: -0.1700
Data Index: 620511 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0718. Min Range: -4.0718
Max Act: 3.6027. Min Act: -0.1700
Data Index: 5398201 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19