Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5577 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4866. Min Range: -11.4866
Max Act: 11.4866. Min Act: -0.1700
Data Index: 2651645 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4866. Min Range: -11.4866
Max Act: 11.2991. Min Act: -0.1700
Data Index: 1656577 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4866. Min Range: -11.4866
Max Act: 11.2366. Min Act: -0.1700
Data Index: 7027716 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4866. Min Range: -11.4866
Max Act: 11.1116. Min Act: -0.1697
Data Index: 27137 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4866. Min Range: -11.4866
Max Act: 11.0491. Min Act: -0.1700
Data Index: 3044686 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.9866. Min Act: -0.1700
Data Index: 955546 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.9866. Min Act: -0.1700
Data Index: 5176726 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.7991. Min Act: -0.1700
Data Index: 2338036 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.8616. Min Act: -0.1700
Data Index: 5054559 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.7366. Min Act: -0.1700
Data Index: 1641555 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.7366. Min Act: -0.1700
Data Index: 3884148 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.7366. Min Act: -0.1700
Data Index: 7247993 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.6741. Min Act: -0.1700
Data Index: 4448732 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.6741. Min Act: -0.1700
Data Index: 88688 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.6741. Min Act: -0.1700
Data Index: 4525551 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.6741. Min Act: -0.1700
Data Index: 2200484 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.6116. Min Act: -0.1700
Data Index: 4318546 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.6741. Min Act: -0.1700
Data Index: 6465777 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.6116. Min Act: -0.1700
Data Index: 4968711 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4866. Min Range: -11.4866
Max Act: 10.5491. Min Act: -0.1700
Data Index: 5881114 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19