Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2017. Min Range: -4.2017
Max Act: 4.2017. Min Act: -0.1700
Data Index: 4912848 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2017. Min Range: -4.2017
Max Act: 4.1079. Min Act: -0.1700
Data Index: 6980427 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2017. Min Range: -4.2017
Max Act: 4.0766. Min Act: -0.1700
Data Index: 5627524 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2017. Min Range: -4.2017
Max Act: 4.0454. Min Act: -0.1700
Data Index: 4019299 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2017. Min Range: -4.2017
Max Act: 4.0141. Min Act: -0.1700
Data Index: 2870664 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9829. Min Act: -0.1700
Data Index: 637840 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9829. Min Act: -0.1700
Data Index: 4914359 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2017. Min Range: -4.2017
Max Act: 4.0141. Min Act: -0.1700
Data Index: 8446630 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9516. Min Act: -0.1700
Data Index: 7592315 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9360. Min Act: -0.1700
Data Index: 5079418 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9203. Min Act: -0.1700
Data Index: 4821079 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9203. Min Act: -0.1700
Data Index: 7915665 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9047. Min Act: -0.1700
Data Index: 1966559 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9047. Min Act: -0.1700
Data Index: 2305383 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9047. Min Act: -0.1700
Data Index: 1550100 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9047. Min Act: -0.1700
Data Index: 4925709 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9047. Min Act: -0.1700
Data Index: 2174975 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.9047. Min Act: -0.1700
Data Index: 8223873 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.8891. Min Act: -0.1700
Data Index: 6787347 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2017. Min Range: -4.2017
Max Act: 3.8891. Min Act: -0.1700
Data Index: 2855376 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19