Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.3754. Min Act: -0.1700
Data Index: 7661967 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.2817. Min Act: -0.1700
Data Index: 7783347 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.2504. Min Act: -0.1700
Data Index: 4509070 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.2192. Min Act: -0.1700
Data Index: 4343367 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.2192. Min Act: -0.1700
Data Index: 3159750 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.2192. Min Act: -0.1700
Data Index: 7175987 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.1254. Min Act: -0.1700
Data Index: 5651854 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0942. Min Act: -0.1700
Data Index: 3099853 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0629. Min Act: -0.1700
Data Index: 5547130 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0004. Min Act: -0.1700
Data Index: 8330916 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0004. Min Act: -0.1700
Data Index: 4879734 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0004. Min Act: -0.1700
Data Index: 8818635 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3754. Min Range: -6.3754
Max Act: 6.0004. Min Act: -0.1700
Data Index: 2796454 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9692. Min Act: -0.1700
Data Index: 6582780 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9692. Min Act: -0.1700
Data Index: 3047324 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9379. Min Act: -0.1700
Data Index: 6108261 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9379. Min Act: -0.1700
Data Index: 160740 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9379. Min Act: -0.1700
Data Index: 4462482 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9067. Min Act: -0.1700
Data Index: 8482538 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3754. Min Range: -6.3754
Max Act: 5.9067. Min Act: -0.1700
Data Index: 6463848 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19