Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1472 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1845. Min Act: -0.1700
Data Index: 1115325 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1687. Min Act: -0.1700
Data Index: 8778385 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1687. Min Act: -0.1700
Data Index: 4350906 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1373. Min Act: -0.1700
Data Index: 3372284 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1373. Min Act: -0.1700
Data Index: 8091022 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1057. Min Act: -0.1700
Data Index: 3975054 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1215. Min Act: -0.1700
Data Index: 8816608 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1530. Min Act: -0.1700
Data Index: 3027243 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1530. Min Act: -0.1700
Data Index: 8013677 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1530. Min Act: -0.1700
Data Index: 6264499 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1215. Min Act: -0.1700
Data Index: 8334942 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.0584. Min Act: -0.1700
Data Index: 5141969 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1373. Min Act: -0.1700
Data Index: 6598336 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.0742. Min Act: -0.1700
Data Index: 2585943 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.1215. Min Act: -0.1700
Data Index: 3654015 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.0584. Min Act: -0.1700
Data Index: 1115326 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.0900. Min Act: -0.1700
Data Index: 554458 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.0584. Min Act: -0.1700
Data Index: 2433153 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.0584. Min Act: -0.1700
Data Index: 911844 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1845. Min Range: -3.1845
Max Act: 3.0742. Min Act: -0.1700
Data Index: 5247719 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19