Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4217. Min Range: -7.4217
Max Act: 7.4217. Min Act: -0.1700
Data Index: 2259717 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4217. Min Range: -7.4217
Max Act: 7.2967. Min Act: -0.1700
Data Index: 638572 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4217. Min Range: -7.4217
Max Act: 7.1717. Min Act: -0.1700
Data Index: 1504688 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4217. Min Range: -7.4217
Max Act: 7.0467. Min Act: -0.1700
Data Index: 734479 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.9217. Min Act: -0.1700
Data Index: 4721396 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.9217. Min Act: -0.1700
Data Index: 4286440 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.8592. Min Act: -0.1700
Data Index: 7537500 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.8592. Min Act: -0.1700
Data Index: 2320581 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.7655. Min Act: -0.1700
Data Index: 7356568 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.7655. Min Act: -0.1700
Data Index: 3785490 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.7342. Min Act: -0.1700
Data Index: 2708493 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.6717. Min Act: -0.1700
Data Index: 2328877 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.5780. Min Act: -0.1700
Data Index: 7356567 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.5780. Min Act: -0.1700
Data Index: 7964705 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.5467. Min Act: -0.1700
Data Index: 5284318 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.5155. Min Act: -0.1700
Data Index: 5641073 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.5155. Min Act: -0.1700
Data Index: 4313498 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.5155. Min Act: -0.1700
Data Index: 5598691 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.5155. Min Act: -0.1700
Data Index: 638569 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4217. Min Range: -7.4217
Max Act: 6.3905. Min Act: -0.1700
Data Index: 1867505 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19