Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1695 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.7366. Min Act: -0.1700
Data Index: 5585177 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.7366. Min Act: -0.1700
Data Index: 1467536 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6741. Min Act: -0.1700
Data Index: 5387554 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.7366. Min Act: -0.1700
Data Index: 992386 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.7366. Min Act: -0.1700
Data Index: 288514 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6741. Min Act: -0.1700
Data Index: 5068663 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6741. Min Act: -0.1700
Data Index: 991720 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6741. Min Act: -0.1700
Data Index: 1340593 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6428. Min Act: -0.1700
Data Index: 8065439 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6428. Min Act: -0.1700
Data Index: 8617844 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6428. Min Act: -0.1700
Data Index: 7046545 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6428. Min Act: -0.1700
Data Index: 1828855 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6428. Min Act: -0.1700
Data Index: 6427394 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.5802. Min Act: -0.1700
Data Index: 6759229 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6115. Min Act: -0.1700
Data Index: 233631 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6115. Min Act: -0.1700
Data Index: 6279240 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6428. Min Act: -0.1700
Data Index: 2091363 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6115. Min Act: -0.1700
Data Index: 3227401 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6115. Min Act: -0.1700
Data Index: 5822200 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7366. Min Range: -3.7366
Max Act: 3.6115. Min Act: -0.1700
Data Index: 1428781 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19