Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 313 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.5453. Min Act: -0.1700
Data Index: 2671053 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.4516. Min Act: -0.1700
Data Index: 8758103 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.4203. Min Act: -0.1700
Data Index: 2205230 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.3891. Min Act: -0.1700
Data Index: 6322689 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.3891. Min Act: -0.1700
Data Index: 7805295 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.3578. Min Act: -0.1700
Data Index: 2109260 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.3266. Min Act: -0.1700
Data Index: 2506688 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2641. Min Act: -0.1700
Data Index: 4896939 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2641. Min Act: -0.1700
Data Index: 6688116 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2641. Min Act: -0.1700
Data Index: 8655901 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2328. Min Act: -0.1700
Data Index: 8793272 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2328. Min Act: -0.1700
Data Index: 6046547 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2016. Min Act: -0.1700
Data Index: 4686733 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2328. Min Act: -0.1700
Data Index: 2930246 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2016. Min Act: -0.1700
Data Index: 3216675 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2016. Min Act: -0.1700
Data Index: 6113832 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.2016. Min Act: -0.1700
Data Index: 7682921 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.1703. Min Act: -0.1700
Data Index: 5710910 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.1391. Min Act: -0.1700
Data Index: 2562180 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5453. Min Range: -5.5453
Max Act: 5.1703. Min Act: -0.1700
Data Index: 5612046 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19