Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4841 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1056. Min Range: -4.1056
Max Act: 4.1056. Min Act: -0.1700
Data Index: 6964207 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.9180. Min Act: -0.1700
Data Index: 5625126 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.9024. Min Act: -0.1700
Data Index: 1813789 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.8868. Min Act: -0.1700
Data Index: 8769244 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.8711. Min Act: -0.1700
Data Index: 512013 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.7773. Min Act: -0.1700
Data Index: 7491436 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.7460. Min Act: -0.1700
Data Index: 5840168 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.7304. Min Act: -0.1700
Data Index: 6909443 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6365. Min Act: -0.1700
Data Index: 1930384 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6522. Min Act: -0.1700
Data Index: 4865357 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6365. Min Act: -0.1700
Data Index: 8218794 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6522. Min Act: -0.1700
Data Index: 6656478 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6209. Min Act: -0.1700
Data Index: 2133207 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6052. Min Act: -0.1700
Data Index: 889636 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6052. Min Act: -0.1700
Data Index: 6147073 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6052. Min Act: -0.1700
Data Index: 5337856 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.6052. Min Act: -0.1700
Data Index: 747692 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.5896. Min Act: -0.1700
Data Index: 8439806 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.5739. Min Act: -0.1700
Data Index: 2987951 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1056. Min Range: -4.1056
Max Act: 3.5739. Min Act: -0.1700
Data Index: 8806399 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19