Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1717 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0092. Min Range: -5.0092
Max Act: 5.0092. Min Act: -0.1700
Data Index: 6060728 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6030. Min Act: -0.1700
Data Index: 29756 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 1158504 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 618629 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5405. Min Act: -0.1700
Data Index: 2650109 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5092. Min Act: -0.1700
Data Index: 935725 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4780. Min Act: -0.1700
Data Index: 6011067 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4780. Min Act: -0.1700
Data Index: 5946364 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4467. Min Act: -0.1700
Data Index: 2333999 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4467. Min Act: -0.1700
Data Index: 1256911 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4155. Min Act: -0.1700
Data Index: 4869742 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4780. Min Act: -0.1700
Data Index: 7151809 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4155. Min Act: -0.1700
Data Index: 4604849 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4155. Min Act: -0.1700
Data Index: 3885512 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4155. Min Act: -0.1700
Data Index: 3663826 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.3842. Min Act: -0.1700
Data Index: 7553696 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.3530. Min Act: -0.1700
Data Index: 524036 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.3842. Min Act: -0.1700
Data Index: 6163112 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.3530. Min Act: -0.1700
Data Index: 1413493 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.3530. Min Act: -0.1700
Data Index: 3114217 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19