Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.4880. Min Act: -0.1700
Data Index: 3886842 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.4255. Min Act: -0.1700
Data Index: 628659 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.3630. Min Act: -0.1700
Data Index: 2389039 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2693. Min Act: -0.1700
Data Index: 4556791 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2693. Min Act: -0.1700
Data Index: 919304 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2693. Min Act: -0.1700
Data Index: 3030940 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2068. Min Act: -0.1700
Data Index: 1131312 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2068. Min Act: -0.1700
Data Index: 5354823 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1755. Min Act: -0.1700
Data Index: 6476685 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2068. Min Act: -0.1700
Data Index: 892139 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2068. Min Act: -0.1700
Data Index: 1018648 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.2068. Min Act: -0.1700
Data Index: 5405653 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1755. Min Act: -0.1700
Data Index: 34615 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1755. Min Act: -0.1700
Data Index: 5504409 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1755. Min Act: -0.1700
Data Index: 1185425 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1755. Min Act: -0.1700
Data Index: 8738594 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1755. Min Act: -0.1700
Data Index: 5377037 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1755. Min Act: -0.1700
Data Index: 4132090 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1443. Min Act: -0.1700
Data Index: 5658035 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4880. Min Range: -4.4880
Max Act: 4.1443. Min Act: -0.1700
Data Index: 1029948 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19