Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.9732. Min Act: -0.1699
Data Index: 2734475 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.9732. Min Act: -0.1700
Data Index: 8319592 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.9732. Min Act: -0.1700
Data Index: 2943012 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.9732. Min Act: -0.1700
Data Index: 6998917 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.9107. Min Act: -0.1700
Data Index: 6819522 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.9107. Min Act: -0.1700
Data Index: 8804184 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 3492525 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 5050731 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7738448 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 3475034 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 1431059 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 1403712 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 6922611 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.8482. Min Act: -0.1700
Data Index: 3172907 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.7857. Min Act: -0.1700
Data Index: 5275390 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4773071 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.7857. Min Act: -0.1700
Data Index: 960616 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.7857. Min Act: -0.1700
Data Index: 2063862 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.7857. Min Act: -0.1700
Data Index: 805946 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9732. Min Range: -6.9732
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4889738 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19