Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3373 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2895. Min Range: -5.2895
Max Act: 5.2895. Min Act: -0.1700
Data Index: 5514079 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2895. Min Range: -5.2895
Max Act: 5.1333. Min Act: -0.1700
Data Index: 2172296 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2895. Min Range: -5.2895
Max Act: 5.1645. Min Act: -0.1700
Data Index: 2473332 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2895. Min Range: -5.2895
Max Act: 5.1333. Min Act: -0.1700
Data Index: 954883 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2895. Min Range: -5.2895
Max Act: 5.0708. Min Act: -0.1700
Data Index: 6973991 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2895. Min Range: -5.2895
Max Act: 5.1020. Min Act: -0.1700
Data Index: 6888861 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.9458. Min Act: -0.1700
Data Index: 7677427 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.9458. Min Act: -0.1700
Data Index: 4943440 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.9145. Min Act: -0.1700
Data Index: 406134 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.9145. Min Act: -0.1700
Data Index: 7559361 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.9145. Min Act: -0.1700
Data Index: 3857257 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.8833. Min Act: -0.1700
Data Index: 3741443 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.8833. Min Act: -0.1700
Data Index: 1647668 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.8833. Min Act: -0.1700
Data Index: 3175168 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.7895. Min Act: -0.1700
Data Index: 3880096 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.8520. Min Act: -0.1700
Data Index: 7441818 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.7895. Min Act: -0.1700
Data Index: 6140549 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.8208. Min Act: -0.1700
Data Index: 5953744 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.8520. Min Act: -0.1700
Data Index: 5036402 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2895. Min Range: -5.2895
Max Act: 4.8208. Min Act: -0.1700
Data Index: 1363716 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19