Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 525 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.9828. Min Act: -0.1700
Data Index: 579980 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.9516. Min Act: -0.1700
Data Index: 5393794 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.7953. Min Act: -0.1700
Data Index: 4309686 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.6078. Min Act: -0.1700
Data Index: 6009751 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.5766. Min Act: -0.1700
Data Index: 6823360 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.5766. Min Act: -0.1700
Data Index: 8163437 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.6078. Min Act: -0.1700
Data Index: 776517 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.6078. Min Act: -0.1700
Data Index: 2352920 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.5453. Min Act: -0.1700
Data Index: 6689011 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.5453. Min Act: -0.1700
Data Index: 227803 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.5141. Min Act: -0.1700
Data Index: 2870767 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.5453. Min Act: -0.1700
Data Index: 7049783 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.4516. Min Act: -0.1700
Data Index: 3532273 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.4203. Min Act: -0.1700
Data Index: 8126589 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.4203. Min Act: -0.1700
Data Index: 607047 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.3891. Min Act: -0.1700
Data Index: 1772204 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.3891. Min Act: -0.1700
Data Index: 6915904 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.3266. Min Act: -0.1700
Data Index: 6874364 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.3891. Min Act: -0.1700
Data Index: 7480826 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9828. Min Range: -6.9828
Max Act: 6.3578. Min Act: -0.1700
Data Index: 2959847 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19