Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5967 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.3775. Min Act: -0.1700
Data Index: 5428009 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.2212. Min Act: -0.1700
Data Index: 6867851 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1587. Min Act: -0.1700
Data Index: 7594715 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1587. Min Act: -0.1700
Data Index: 903427 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1587. Min Act: -0.1700
Data Index: 150452 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1275. Min Act: -0.1700
Data Index: 8670121 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0650. Min Act: -0.1700
Data Index: 439225 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7627637 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0650. Min Act: -0.1700
Data Index: 6434137 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0650. Min Act: -0.1700
Data Index: 3360593 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7284975 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 6298802 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 5387871 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 4370172 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3775. Min Range: -5.3775
Max Act: 4.9712. Min Act: -0.1700
Data Index: 6294013 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0025. Min Act: -0.1700
Data Index: 5631379 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0025. Min Act: -0.1700
Data Index: 2508966 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3775. Min Range: -5.3775
Max Act: 4.9712. Min Act: -0.1700
Data Index: 5615316 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0025. Min Act: -0.1700
Data Index: 743897 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3775. Min Range: -5.3775
Max Act: 4.9712. Min Act: -0.1700
Data Index: 8441976 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19