Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1872. Min Range: -6.1872
Max Act: 6.1872. Min Act: -0.1700
Data Index: 7435042 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1872. Min Range: -6.1872
Max Act: 6.0622. Min Act: -0.1700
Data Index: 568391 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.9997. Min Act: -0.1700
Data Index: 3589955 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.9372. Min Act: -0.1700
Data Index: 6065497 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.9059. Min Act: -0.1700
Data Index: 1496524 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8747. Min Act: -0.1700
Data Index: 8587394 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.9059. Min Act: -0.1700
Data Index: 7063193 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8747. Min Act: -0.1700
Data Index: 5210535 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8747. Min Act: -0.1700
Data Index: 4304299 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8122. Min Act: -0.1700
Data Index: 7600378 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8434. Min Act: -0.1700
Data Index: 4018641 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8122. Min Act: -0.1700
Data Index: 2354599 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8122. Min Act: -0.1700
Data Index: 1010308 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8434. Min Act: -0.1700
Data Index: 3552470 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8122. Min Act: -0.1700
Data Index: 8498780 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.7809. Min Act: -0.1700
Data Index: 4013243 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.7809. Min Act: -0.1700
Data Index: 1980354 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.8122. Min Act: -0.1700
Data Index: 5849458 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.7809. Min Act: -0.1700
Data Index: 4372942 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1872. Min Range: -6.1872
Max Act: 5.7184. Min Act: -0.1700
Data Index: 4807776 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19