Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2251 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.2616. Min Act: -0.1700
Data Index: 6234215 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.2303. Min Act: -0.1700
Data Index: 5293808 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1991. Min Act: -0.1700
Data Index: 96805 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1991. Min Act: -0.1700
Data Index: 4034285 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1991. Min Act: -0.1700
Data Index: 6981064 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1991. Min Act: -0.1700
Data Index: 6051045 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1678. Min Act: -0.1700
Data Index: 822536 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1678. Min Act: -0.1700
Data Index: 6680243 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1365. Min Act: -0.1700
Data Index: 122024 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1365. Min Act: -0.1700
Data Index: 8198818 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1365. Min Act: -0.1700
Data Index: 695184 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1365. Min Act: -0.1700
Data Index: 6994292 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.0740. Min Act: -0.1700
Data Index: 3764107 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1053. Min Act: -0.1700
Data Index: 8140202 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.0740. Min Act: -0.1700
Data Index: 2858913 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1053. Min Act: -0.1700
Data Index: 557548 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1053. Min Act: -0.1700
Data Index: 945243 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1053. Min Act: -0.1700
Data Index: 5445966 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1365. Min Act: -0.1700
Data Index: 6643435 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2616. Min Range: -4.2616
Max Act: 4.1053. Min Act: -0.1700
Data Index: 6586618 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19