Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1243 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.4623. Min Act: -0.1700
Data Index: 2537928 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.4310. Min Act: -0.1700
Data Index: 227526 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.3373. Min Act: -0.1700
Data Index: 3293188 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.3060. Min Act: -0.1700
Data Index: 1719522 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.2748. Min Act: -0.1700
Data Index: 227523 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.2123. Min Act: -0.1700
Data Index: 6539596 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1810. Min Act: -0.1700
Data Index: 3429234 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.2123. Min Act: -0.1699
Data Index: 7158317 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1498. Min Act: -0.1699
Data Index: 3466883 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1810. Min Act: -0.1700
Data Index: 7158319 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1810. Min Act: -0.1700
Data Index: 154315 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1498. Min Act: -0.1700
Data Index: 227522 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1498. Min Act: -0.1700
Data Index: 943054 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1498. Min Act: -0.1700
Data Index: 7242533 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1498. Min Act: -0.1700
Data Index: 5265095 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1498. Min Act: -0.1700
Data Index: 4100197 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1185. Min Act: -0.1698
Data Index: 5265101 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.1185. Min Act: -0.1700
Data Index: 1719521 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.0873. Min Act: -0.1700
Data Index: 2439522 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4623. Min Range: -5.4623
Max Act: 5.0873. Min Act: -0.1700
Data Index: 1719518 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19