Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.2558. Min Act: -0.1700
Data Index: 3438978 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1933. Min Act: -0.1700
Data Index: 5742342 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1621. Min Act: -0.1700
Data Index: 1821200 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1933. Min Act: -0.1700
Data Index: 7336910 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 4576349 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 5742357 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 7889032 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 7704847 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 3595922 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 7546056 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 203340 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1699
Data Index: 225867 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 6919206 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.1308. Min Act: -0.1700
Data Index: 8672447 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.0996. Min Act: -0.1700
Data Index: 6657095 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.0996. Min Act: -0.1700
Data Index: 6410445 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.0996. Min Act: -0.1700
Data Index: 1525386 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.0996. Min Act: -0.1699
Data Index: 4379494 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.0683. Min Act: -0.1700
Data Index: 2691541 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2558. Min Range: -6.2558
Max Act: 6.0996. Min Act: -0.1699
Data Index: 8394962 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19