Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1693 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.4057. Min Act: -0.1700
Data Index: 2171951 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.3119. Min Act: -0.1700
Data Index: 6432939 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.2807. Min Act: -0.1700
Data Index: 996533 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.2182. Min Act: -0.1700
Data Index: 6958340 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.2494. Min Act: -0.1700
Data Index: 1669061 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1869. Min Act: -0.1700
Data Index: 6730959 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1869. Min Act: -0.1700
Data Index: 4549355 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1557. Min Act: -0.1700
Data Index: 6292219 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.2182. Min Act: -0.1700
Data Index: 8685697 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1557. Min Act: -0.1700
Data Index: 4047518 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1557. Min Act: -0.1700
Data Index: 2394185 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1244. Min Act: -0.1700
Data Index: 4957935 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1244. Min Act: -0.1700
Data Index: 1360017 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.1557. Min Act: -0.1700
Data Index: 4409586 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.0931. Min Act: -0.1700
Data Index: 7889757 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.0931. Min Act: -0.1700
Data Index: 4523501 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.0619. Min Act: -0.1700
Data Index: 7447150 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.0619. Min Act: -0.1700
Data Index: 5909547 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.0619. Min Act: -0.1700
Data Index: 2607366 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4057. Min Range: -4.4057
Max Act: 4.0619. Min Act: -0.1700
Data Index: 95067 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19