Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 770 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.2324. Min Act: -0.1700
Data Index: 8496424 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1387. Min Act: -0.1700
Data Index: 5912916 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1699. Min Act: -0.1699
Data Index: 4641217 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1699. Min Act: -0.1700
Data Index: 5534765 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1387. Min Act: -0.1700
Data Index: 2171057 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1387. Min Act: -0.1700
Data Index: 4649536 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1074. Min Act: -0.1700
Data Index: 2425828 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1074. Min Act: -0.1700
Data Index: 265803 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1074. Min Act: -0.1700
Data Index: 5401102 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1074. Min Act: -0.1700
Data Index: 5423254 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1074. Min Act: -0.1700
Data Index: 956069 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.1074. Min Act: -0.1700
Data Index: 7480749 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0762. Min Act: -0.1699
Data Index: 6376911 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0762. Min Act: -0.1700
Data Index: 2555804 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0762. Min Act: -0.1700
Data Index: 2927725 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0762. Min Act: -0.1700
Data Index: 1785435 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0449. Min Act: -0.1700
Data Index: 4001117 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0449. Min Act: -0.1700
Data Index: 1542807 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0449. Min Act: -0.1700
Data Index: 2728206 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2324. Min Range: -5.2324
Max Act: 5.0449. Min Act: -0.1700
Data Index: 4425978 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19