Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.5160. Min Act: -0.1700
Data Index: 3449997 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.4848. Min Act: -0.1700
Data Index: 2607682 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.3910. Min Act: -0.1700
Data Index: 8230856 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.3910. Min Act: -0.1700
Data Index: 7203751 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2973. Min Act: -0.1700
Data Index: 5892319 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2660. Min Act: -0.1700
Data Index: 1335788 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2660. Min Act: -0.1700
Data Index: 8542227 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2973. Min Act: -0.1700
Data Index: 6483492 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2348. Min Act: -0.1700
Data Index: 4734365 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2035. Min Act: -0.1700
Data Index: 4734366 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.1723. Min Act: -0.1700
Data Index: 4188419 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2035. Min Act: -0.1700
Data Index: 4641713 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2035. Min Act: -0.1700
Data Index: 4538368 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2035. Min Act: -0.1700
Data Index: 6513311 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.2035. Min Act: -0.1700
Data Index: 7963392 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.1410. Min Act: -0.1700
Data Index: 777305 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.1723. Min Act: -0.1700
Data Index: 7718496 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.1410. Min Act: -0.1700
Data Index: 399926 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.0785. Min Act: -0.1700
Data Index: 4349945 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5160. Min Range: -6.5160
Max Act: 6.1098. Min Act: -0.1700
Data Index: 4962810 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19