Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4998. Min Act: -0.1700
Data Index: 3995558 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4685. Min Act: -0.1700
Data Index: 1086412 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4372. Min Act: -0.1700
Data Index: 5669646 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3274. Min Act: -0.1700
Data Index: 7439265 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.3117. Min Act: -0.1700
Data Index: 8391606 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2017. Min Act: -0.1700
Data Index: 5696560 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.2017. Min Act: -0.1700
Data Index: 5477339 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.1545. Min Act: -0.1700
Data Index: 3894563 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0915. Min Act: -0.1700
Data Index: 6575813 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0915. Min Act: -0.1700
Data Index: 298339 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0757. Min Act: -0.1700
Data Index: 8173093 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0757. Min Act: -0.1700
Data Index: 1754011 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0442. Min Act: -0.1700
Data Index: 4329383 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0442. Min Act: -0.1700
Data Index: 208492 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0442. Min Act: -0.1700
Data Index: 6383361 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0442. Min Act: -0.1700
Data Index: 7910381 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0126. Min Act: -0.1700
Data Index: 1517060 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0284. Min Act: -0.1700
Data Index: 4043246 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0284. Min Act: -0.1700
Data Index: 6956904 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.0284. Min Act: -0.1700
Data Index: 3204793 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19