Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.8183. Min Act: -0.1700
Data Index: 7097398 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.7870. Min Act: -0.1700
Data Index: 7091869 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.7558. Min Act: -0.1700
Data Index: 1275669 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.7558. Min Act: -0.1700
Data Index: 5794223 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.7245. Min Act: -0.1700
Data Index: 6169979 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.6620. Min Act: -0.1700
Data Index: 2507090 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.6308. Min Act: -0.1700
Data Index: 4376785 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5995. Min Act: -0.1700
Data Index: 2040533 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.6308. Min Act: -0.1700
Data Index: 1432916 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5370. Min Act: -0.1700
Data Index: 1455278 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5995. Min Act: -0.1700
Data Index: 4616436 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5683. Min Act: -0.1700
Data Index: 6533939 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5683. Min Act: -0.1700
Data Index: 3230874 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5995. Min Act: -0.1700
Data Index: 354722 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5058. Min Act: -0.1700
Data Index: 3581653 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.4745. Min Act: -0.1700
Data Index: 146221 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5058. Min Act: -0.1700
Data Index: 7091875 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.4745. Min Act: -0.1700
Data Index: 7514046 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.5370. Min Act: -0.1700
Data Index: 3138675 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8183. Min Range: -5.8183
Max Act: 5.4745. Min Act: -0.1700
Data Index: 2027811 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19