Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4455 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.4317. Min Act: -0.1700
Data Index: 4375562 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 7158975 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 239776 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 2112865 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.3067. Min Act: -0.1700
Data Index: 98789 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.2442. Min Act: -0.1700
Data Index: 2934528 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.1817. Min Act: -0.1700
Data Index: 8515042 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.1817. Min Act: -0.1700
Data Index: 1465849 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.1192. Min Act: -0.1700
Data Index: 1991254 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.1192. Min Act: -0.1700
Data Index: 1077591 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4317. Min Range: -8.4317
Max Act: 8.0567. Min Act: -0.1700
Data Index: 4517619 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.9942. Min Act: -0.1700
Data Index: 5484588 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.9942. Min Act: -0.1700
Data Index: 2171813 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.9942. Min Act: -0.1700
Data Index: 1985115 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.9317. Min Act: -0.1700
Data Index: 3908914 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.9317. Min Act: -0.1700
Data Index: 3208570 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.9317. Min Act: -0.1700
Data Index: 8783989 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.8692. Min Act: -0.1700
Data Index: 535771 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.8692. Min Act: -0.1700
Data Index: 1261850 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4317. Min Range: -8.4317
Max Act: 7.9317. Min Act: -0.1700
Data Index: 4950667 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19