Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4647 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0162. Min Range: -9.0162
Max Act: 9.0162. Min Act: -0.1700
Data Index: 7407357 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.9537. Min Act: -0.1700
Data Index: 8244304 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.6412. Min Act: -0.1700
Data Index: 4035170 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.4537. Min Act: -0.1700
Data Index: 2008145 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.3912. Min Act: -0.1700
Data Index: 6144299 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.3287. Min Act: -0.1700
Data Index: 1373849 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.3287. Min Act: -0.1700
Data Index: 5520559 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.2662. Min Act: -0.1700
Data Index: 1373848 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.3287. Min Act: -0.1700
Data Index: 8792660 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.2662. Min Act: -0.1700
Data Index: 7289570 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.2037. Min Act: -0.1700
Data Index: 1790116 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.2037. Min Act: -0.1700
Data Index: 7648329 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.1724. Min Act: -0.1700
Data Index: 5378708 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.1724. Min Act: -0.1700
Data Index: 265888 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.1412. Min Act: -0.1700
Data Index: 5426120 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.1412. Min Act: -0.1700
Data Index: 8071625 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.1412. Min Act: -0.1700
Data Index: 5606664 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.0474. Min Act: -0.1700
Data Index: 6925393 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.1099. Min Act: -0.1700
Data Index: 5091308 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0162. Min Range: -9.0162
Max Act: 8.0787. Min Act: -0.1700
Data Index: 5190477 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19