Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0997. Min Range: -8.0997
Max Act: 8.0997. Min Act: -0.1700
Data Index: 6664832 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9747. Min Act: -0.1700
Data Index: 1771297 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9747. Min Act: -0.1700
Data Index: 1061770 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9747. Min Act: -0.1700
Data Index: 1352725 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9747. Min Act: -0.1700
Data Index: 1171260 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9434. Min Act: -0.1700
Data Index: 5725599 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9122. Min Act: -0.1700
Data Index: 5872503 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9122. Min Act: -0.1700
Data Index: 8616578 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9434. Min Act: -0.1700
Data Index: 5962681 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9122. Min Act: -0.1700
Data Index: 6450852 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9122. Min Act: -0.1700
Data Index: 1632859 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9122. Min Act: -0.1700
Data Index: 1356112 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.9122. Min Act: -0.1700
Data Index: 6264158 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.8184. Min Act: -0.1700
Data Index: 8266498 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.8184. Min Act: -0.1700
Data Index: 4913012 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.8184. Min Act: -0.1700
Data Index: 4531635 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.7872. Min Act: -0.1700
Data Index: 8254109 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.6934. Min Act: -0.1700
Data Index: 3291134 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.7247. Min Act: -0.1700
Data Index: 5688953 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0997. Min Range: -8.0997
Max Act: 7.7559. Min Act: -0.1700
Data Index: 4554570 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19