Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0404. Min Range: -4.0404
Max Act: 4.0404. Min Act: -0.1700
Data Index: 3130155 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0404. Min Range: -4.0404
Max Act: 4.0404. Min Act: -0.1700
Data Index: 6257579 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0404. Min Range: -4.0404
Max Act: 4.0092. Min Act: -0.1700
Data Index: 597313 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 8160707 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0404. Min Range: -4.0404
Max Act: 4.0092. Min Act: -0.1700
Data Index: 2712413 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9623. Min Act: -0.1700
Data Index: 2115012 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 2833592 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 8224190 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 4282129 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9623. Min Act: -0.1700
Data Index: 8621375 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 3080096 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 6390154 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 6030194 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 3398960 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9623. Min Act: -0.1700
Data Index: 1089146 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9623. Min Act: -0.1700
Data Index: 8439747 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9623. Min Act: -0.1700
Data Index: 5787086 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9623. Min Act: -0.1700
Data Index: 6444530 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 3685230 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9623. Min Act: -0.1700
Data Index: 2275242 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19