Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4418 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.6634. Min Act: -0.1700
Data Index: 1058452 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5992. Min Act: -0.1700
Data Index: 2158208 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.6153. Min Act: -0.1700
Data Index: 5027456 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5670. Min Act: -0.1700
Data Index: 486846 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5670. Min Act: -0.1700
Data Index: 3167280 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1715714 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5670. Min Act: -0.1700
Data Index: 4144249 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5670. Min Act: -0.1700
Data Index: 7608844 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5185. Min Act: -0.1700
Data Index: 8298241 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5185. Min Act: -0.1700
Data Index: 4892783 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5185. Min Act: -0.1700
Data Index: 7739009 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5185. Min Act: -0.1700
Data Index: 5208943 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.4861. Min Act: -0.1700
Data Index: 7614321 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.4861. Min Act: -0.1700
Data Index: 5622497 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5023. Min Act: -0.1700
Data Index: 6176056 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5023. Min Act: -0.1700
Data Index: 3577496 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.4861. Min Act: -0.1700
Data Index: 4853167 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.4861. Min Act: -0.1700
Data Index: 5393192 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.5023. Min Act: -0.1700
Data Index: 7028351 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6634. Min Range: -2.6634
Max Act: 2.4861. Min Act: -0.1700
Data Index: 4837486 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19